© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154372
    Prev
    Next
    INDEX
    Explanations

    effect or alignment

    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_60_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
    ,…
    0.49
     их
    0.44
     自
    0.42
     его
    0.41
    Walking
    0.41
    …?
    0.41
    ?...
    0.41
     母
    0.40
     त
    0.40
    ,...
    0.40
    POSITIVE LOGITS
    ab
    0.55
    and
    0.54
    ul
    0.54
    ur
    0.52
    fr
    0.51
     and
    0.50
    au
    0.49
    ou
    0.49
    enter
    0.48
    il
    0.48
    Activations Density 0.000%

    No Known Activations