© 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-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62695
    Prev
    Next
    INDEX
    Explanations

    word fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <
    1.90
    <
    1.87
    )<
    1.43
    .<
    1.41
    。<
    1.41
    }<
    1.38
    ,<
    1.37
    :<
    1.36
     "<
    1.34
    ;<
    1.32
    POSITIVE LOGITS
     obsol
    0.40
     biol
    0.37
     statutory
    0.36
     absor
    0.36
     McQu
    0.35
     सृ
    0.35
     いたし
    0.34
     wrink
    0.34
     pestic
    0.34
     odol
    0.33
    Activations Density 0.088%

    No Known Activations