© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208055
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_56_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
    Type
    0.68
     Type
    0.52
    TYPE
    0.52
    sType
    0.50
    TypeDef
    0.49
     const
    0.49
    etype
    0.45
    Τ
    0.45
    T
    0.44
     टाइप
    0.43
    POSITIVE LOGITS
    ვლ
    0.39
     hyd
    0.36
    ኼ
    0.36
     ua
    0.35
     kubb
    0.35
     сове
    0.34
     UA
    0.34
     মান
    0.34
     포함
    0.33
     военных
    0.33
    Activations Density 0.022%

    No Known Activations