© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48873
    Prev
    Next
    INDEX
    Explanations

    list item formatting

    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_31_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
     יד
    0.36
    ㈢
    0.34
     www
    0.34
     টাইমস
    0.34
     ktoś
    0.34
     Composition
    0.34
    IsNullOrEmpty
    0.33
    rono
    0.33
    Izq
    0.33
    距离
    0.33
    POSITIVE LOGITS
     workaround
    0.37
     nicknames
    0.37
     comentar
    0.37
    мыми
    0.36
    軲
    0.35
     loans
    0.35
     bribery
    0.35
     रुका
    0.35
     regard
    0.35
     குறிப்பாக
    0.35
    Activations Density 0.010%

    No Known Activations