© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    words terminated by commas or question marks, words "up there", or words related to giving testimony.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Yes
    -0.84
     Yes
    -0.84
     Sorry
    -0.76
    Maybe
    -0.74
    Sorry
    -0.73
    Oh
    -0.73
     Oh
    -0.71
     Maybe
    -0.70
     yes
    -0.70
    Okay
    -0.70
    POSITIVE LOGITS
    ']]
    0.66
    "]]
    0.58
    ）』
    0.57
    ();*/
    0.57
    中略
    0.56
    ]").
    0.56
    "]').
    0.56
     】
    0.54
    }}">
    0.54
    */,
    0.54
    Activations Density 7.074%

    No Known Activations