© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216375
    Prev
    Next
    INDEX
    Explanations

    character names

    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_50_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
    IAM
    0.43
    stamp
    0.39
     stamp
    0.37
     slamming
    0.37
    揶
    0.36
     Vez
    0.36
    ЕС
    0.35
    Stamp
    0.35
     VEGF
    0.35
    AES
    0.35
    POSITIVE LOGITS
    urde
    0.43
    urando
    0.42
    urr
    0.40
    ວກ
    0.40
    obiettivo
    0.38
     rehe
    0.38
     D
    0.38
    ছা
    0.38
    포츠
    0.37
     बनते
    0.37
    Activations Density 0.000%

    No Known Activations