© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141971
    Prev
    Next
    INDEX
    Explanations

    git diff symbols

    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_46_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
    ോ
    0.43
    ціона
    0.38
    essive
    0.37
    ્ષ
    0.37
    étel
    0.36
    TreeClassifier
    0.35
     assimilate
    0.35
    ल्फी
    0.34
     sConfig
    0.34
    铒
    0.34
    POSITIVE LOGITS
     STANDARD
    0.39
     PZ
    0.39
     PNG
    0.38
     std
    0.38
     Александра
    0.37
    legal
    0.37
     giurid
    0.36
    PSW
    0.36
    legen
    0.36
     Alexandre
    0.36
    Activations Density 0.000%

    No Known Activations