© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38792
    Prev
    Next
    INDEX
    Explanations

    programming libraries

    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_57_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
    ᠰ
    0.46
    ft
    0.37
     случа
    0.36
    Austria
    0.36
    alist
    0.36
    generally
    0.35
     வழ
    0.35
    composition
    0.35
    authenticated
    0.35
    ździe
    0.35
    POSITIVE LOGITS
    ++;
    0.37
    ￥
    0.36
     Penalty
    0.35
     Crack
    0.35
     Present
    0.35
     Penny
    0.34
    やか
    0.34
     Missile
    0.33
    EEP
    0.33
     Projection
    0.33
    Activations Density 0.005%

    No Known Activations