© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44629
    Prev
    Next
    INDEX
    Explanations

    Frankfurt, Frankl, Church, Press, Main

    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_3_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
    ل
    0.67
    ;
    0.65
    ↵
    0.63
     of
    0.58
     in
    0.58
     oxid
    0.58
    <0x0D>
    0.55
    </h4>
    0.55
    地的
    0.54
     reap
    0.53
    POSITIVE LOGITS
    ’
    0.70
    شون
    0.59
    اب
    0.56
     Frankfurt
    0.55
    는
    0.55
    geschwindigkeit
    0.55
     Frankfurter
    0.54
    and
    0.51
    డు
    0.51
     Meine
    0.51
    Activations Density 0.007%

    No Known Activations