© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    mentions of taking action/experiencing something or having an opinion about something.

    oai_token-act-pair · gemini-2.0-flash

    foreign language or non-English terms

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

    Not English

    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
     O
    -0.79
     B
    -0.68
     W
    -0.65
     L
    -0.64
     K
    -0.63
     N
    -0.63
     We
    -0.63
     Z
    -0.62
     v
    -0.62
     r
    -0.62
    POSITIVE LOGITS
     فريبيس
    1.17
    RenderAtEndOf
    1.09
     للاسماء
    1.05
     quæ
    1.05
     étoient
    1.01
     avoient
    0.96
     étoit
    0.94
     feroit
    0.94
     صوتيه
    0.94
     auroit
    0.93
    Activations Density 2.465%

    No Known Activations