© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    uses of the word 'fact' and phrases about saying something to someone

    oai_token-act-pair · gemini-2.0-flash

    statements of fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    aarrggbb
    -0.74
    CloseOperation
    -0.65
     ModelExpression
    -0.62
    ImageContext
    -0.62
    :+:
    -0.60
     Akismet
    -0.60
    SizeF
    -0.59
    ]));
    -0.57
     continúas
    -0.57
    ⓘ
    -0.56
    POSITIVE LOGITS
    lably
    0.47
     odkazy
    0.47
     dourada
    0.47
     navel
    0.47
    MCT
    0.47
    Geograf
    0.46
    ưởng
    0.45
     MCT
    0.44
    cadilly
    0.44
    пот
    0.43
    Activations Density 1.475%

    No Known Activations