© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85662
    Prev
    Next
    INDEX
    Explanations

    closing punctuation marks

    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_18_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
    Khokhlov
    0.02
    zynarod
    0.02
     ఏద
    0.02
    HasStarred
    0.02
    followfollow
    0.02
     성공
    0.02
     设计
    0.02
     让
    0.02
    뷊
    0.02
    --’
    0.02
    POSITIVE LOGITS
     of
    0.02
     are
    0.02
    of
    0.02
     at
    0.02
     in
    0.02
    ti
    0.02
     on
    0.02
    0.02
    alk
    0.02
     maintain
    0.02
    Activations Density 0.001%

    No Known Activations