© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    the word "different" or forms of it, sometimes in conjunction with words indicating plurality such as "types", "several", or "many".

    oai_token-act-pair · gemini-2.0-flash

    classifications or types

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

    different

    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
     different
    -1.75
    different
    -1.72
    Different
    -1.63
     Different
    -1.59
     DIFFERENT
    -1.37
     diferentes
    -1.31
     différentes
    -1.30
    不同的
    -1.28
    不同
    -1.24
     différents
    -1.24
    POSITIVE LOGITS
     types
    0.74
     kinds
    0.68
     références
    0.63
    GraphicsUnit
    0.59
     sorts
    0.58
     but
    0.54
    例文帳に追加
    0.54
    ⓧ
    0.53
     routes
    0.51
     schemes
    0.50
    Activations Density 1.575%

    No Known Activations