© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213515
    Prev
    Next
    INDEX
    Explanations

    format information

    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_47_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
    downcase
    0.45
    ownik
    0.40
    笵
    0.40
     phrases
    0.39
     supporting
    0.39
    leans
    0.38
    ынша
    0.38
    supporting
    0.38
     धाराओं
    0.37
     dico
    0.37
    POSITIVE LOGITS
     Format
    0.43
    読み
    0.41
     format
    0.39
    रज
    0.38
     Kip
    0.38
    ']>;
    0.38
    Format
    0.37
    ней
    0.37
     formats
    0.37
    format
    0.36
    Activations Density 0.005%

    No Known Activations