© 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. 248845
    Prev
    Next
    INDEX
    Explanations

    rock

    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
    ಟ್ಟ
    0.37
    stripped
    0.34
     کنگ
    0.33
    eosin
    0.33
    蒂
    0.33
    usp
    0.32
    好吃
    0.32
    wezig
    0.31
    ocat
    0.31
    गें
    0.31
    POSITIVE LOGITS
     rock
    3.14
     Rock
    2.50
    rock
    2.45
    Rock
    2.39
     ROCK
    2.31
     prov
    2.30
     рок
    2.05
    ROCK
    2.00
    prov
    1.98
    岩
    1.95
    Activations Density 0.004%

    No Known Activations