© 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. 215253
    Prev
    Next
    INDEX
    Explanations

    search for ticket or replacement

    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
    ᱪ
    0.33
    गार
    0.32
    ச்சார
    0.32
     fein
    0.31
    vote
    0.30
     creciendo
    0.30
    enite
    0.29
    heri
    0.29
     kalangan
    0.29
    }+...+\
    0.29
    POSITIVE LOGITS
    แทน
    0.37
    替代
    0.36
    Replacement
    0.35
    代替
    0.33
    න්න
    0.32
     alternative
    0.31
     Replacement
    0.31
     ersetzt
    0.31
     Crook
    0.31
     trunk
    0.30
    Activations Density 0.000%

    No Known Activations