© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13176
    Prev
    Next
    INDEX
    Explanations

    the word "idea" and associated words like think, thought, reason, truth, computer, CMS, and virtues.

    oai_token-act-pair · gemini-2.0-flash

    idea/thought

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ModelRenderer
    -0.70
    AnchorStyles
    -0.67
    ſelf
    -0.66
     Reſ
    -0.66
     Monfieur
    -0.65
     ſche
    -0.62
     Diſ
    -0.62
    WireFormat
    -0.61
     purpoſe
    -0.60
     Вікі
    -0.59
    POSITIVE LOGITS
    /}.
    0.53
     of
    0.46
    DOCTYPE
    0.45
     formed
    0.44
     <",
    0.43
    vait
    0.42
    HomeAsUpEnabled
    0.42
    렴
    0.42
     on
    0.41
     piece
    0.41
    Activations Density 14.641%

    No Known Activations