© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83629
    Prev
    Next
    INDEX
    Explanations

    setting configuration or size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ти
    1.75
    ون
    1.46
    ל
    1.44
    ות
    1.41
    ларга
    1.33
    ونها
    1.29
    ο
    1.28
    यों
    1.20
    ים
    1.19
    ט
    1.18
    POSITIVE LOGITS
    a
    1.74
    ?
    1.63
     was
    1.58
    o
    1.58
    ;
    1.55
    !
    1.49
    ه
    1.38
     is
    1.37
     at
    1.35
    ,
    1.30
    Activations Density 0.000%

    No Known Activations