© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52461
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ೂ
    0.39
    поряд
    0.39
     ನಡೆ
    0.38
    avacanam
    0.37
     pertinentes
    0.37
    urés
    0.36
    uslararası
    0.36
    Australia
    0.35
    紀錄
    0.35
    }_{+}\
    0.35
    POSITIVE LOGITS
    trib
    0.39
     Tribune
    0.39
     Blind
    0.38
     arrived
    0.37
    Blind
    0.37
     Db
    0.37
     Fabi
    0.37
     trib
    0.37
     promised
    0.37
     skipped
    0.37
    Activations Density 0.000%

    No Known Activations