© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    words related to time or the beginning of things

    oai_token-act-pair · gemini-2.0-flash

    words associated with timing and early actions

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

    something happening early

    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
     GenerationType
    -0.94
    InputBorder
    -0.93
    expandindo
    -0.91
     disambiguazione
    -0.85
    PreferredItem
    -0.84
    Vidite
    -0.81
    kháu
    -0.79
     ModelExpression
    -0.77
    RenderAtEndOf
    -0.75
     الرياضيه
    -0.75
    POSITIVE LOGITS
    .
    0.53
     eccell
    0.50
     and
    0.44
     without
    0.43
     taking
    0.42
     when
    0.42
     codice
    0.41
     --
    0.40
     capables
    0.40
    ,
    0.40
    Activations Density 7.740%

    No Known Activations