© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206259
    Prev
    Next
    INDEX
    Explanations

    code fortran

    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_37_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
    memberNameLink
    0.41
    instrList
    0.39
     மயில
    0.39
     MQ
    0.39
    SAM
    0.38
     BACH
    0.38
    綫
    0.38
     Emulator
    0.38
    MIL
    0.37
    emulator
    0.37
    POSITIVE LOGITS
     shield
    0.44
    パン
    0.42
     shields
    0.42
     Vote
    0.42
     vote
    0.41
    ட்டும்
    0.40
    bling
    0.38
     fabric
    0.38
     c
    0.37
     cunning
    0.37
    Activations Density 0.001%

    No Known Activations