© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8809
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing suitability or typicality

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    uxxxx
    -0.78
    migrationBuilder
    -0.70
     doInBackground
    -0.66
    WithIOException
    -0.65
    setVerticalGroup
    -0.65
    ]]);
    -0.64
    ]));
    -0.64
    كويكب
    -0.64
    })->
    -0.63
    ConstraintMaker
    -0.61
    POSITIVE LOGITS
     ellers
    0.49
    otherwise
    0.46
     senior
    0.46
    generally
    0.44
     تعدى
    0.44
     Rptr
    0.43
    anking
    0.43
     generally
    0.42
     inconnu
    0.41
     otherwise
    0.40
    Activations Density 1.625%

    No Known Activations