© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39080
    Prev
    Next
    INDEX
    Explanations

    accountable

    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_11_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
     сотруд
    0.61
    integrate
    0.55
    </th>
    0.55
     வகை
    0.55
    াপে
    0.54
    disable
    0.54
    یکس
    0.54
    Protein
    0.53
    ریس
    0.52
    ᕗ
    0.52
    POSITIVE LOGITS
    -
    0.72
     d
    0.66
    in
    0.65
    \
    0.63
    es
    0.61
     A
    0.60
    us
    0.59
     artisan
    0.58
    ch
    0.56
    m
    0.55
    Activations Density 0.002%

    No Known Activations