© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    words related to personal feelings and opinions

    oai_token-act-pair · gemini-2.0-flash

    prefixes or terms indicating connection or collaboration

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

    Expressing opinions or openness

    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
     betweenstory
    -0.76
    ftagPool
    -0.68
    tagHelperRunner
    -0.68
    expandindo
    -0.68
    urlpatterns
    -0.68
    ècie
    -0.66
    stateMutability
    -0.65
    цездатний
    -0.65
     Seeder
    -0.64
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
    copyWith
    0.53
    sided
    0.50
    ceral
    0.47
     régionale
    0.46
     thermique
    0.45
     to
    0.44
    ùi
    0.44
     specchio
    0.44
     on
    0.44
     when
    0.44
    Activations Density 1.467%

    No Known Activations