© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15244
    Prev
    Next
    INDEX
    Explanations

    words expressing comparison and relative degree

    oai_token-act-pair · gemini-2.0-flash

    descriptive adjectives and terms related to competency

    np_token-act-pair-logits · gpt-4o-mini

    qualities/descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ความ
    -0.71
     reliability
    -0.71
     solidity
    -0.69
     robustness
    -0.68
     softness
    -0.68
     stability
    -0.68
     toughness
    -0.66
     independence
    -0.66
     freshness
    -0.66
     attractiveness
    -0.65
    POSITIVE LOGITS
     tolerant
    0.72
     psychologically
    0.69
    naments
    0.66
     energetically
    0.66
     literate
    0.66
     financially
    0.65
     raiſ
    0.65
    tagHelperRunner
    0.65
     intolerant
    0.65
    хьтан
    0.64
    Activations Density 6.393%

    No Known Activations