© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11204
    Prev
    Next
    INDEX
    Explanations

    confirmations ("yes","so", "of course") alongside moderate uncertainty ("think")

    oai_token-act-pair · gemini-2.0-flash

    agreement/affirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    /');
    -0.51
     []:
    -0.48
    }")]
    -0.47
    inflate
    -0.46
    endencies
    -0.45
     reper
    -0.44
    AlterField
    -0.44
    TypeID
    -0.44
    ÂN
    -0.43
     kautta
    -0.43
    POSITIVE LOGITS
    Yes
    0.72
    QMetaType
    0.71
     Yes
    0.69
     riuscito
    0.69
     Italijani
    0.66
    хьтан
    0.66
    Jeografia
    0.66
    yes
    0.65
    وعة
    0.65
    OGND
    0.63
    Activations Density 0.911%

    No Known Activations