© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145846
    Prev
    Next
    INDEX
    Explanations

    interpreting information

    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_59_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
     qu
    1.04
    qu
    0.70
     Qu
    0.61
     La
    0.51
    there
    0.48
    quat
    0.48
     ש
    0.46
     there
    0.44
     AND
    0.44
     steamers
    0.42
    POSITIVE LOGITS
     il
    0.46
     propri
    0.44
    ीय
    0.42
     naturali
    0.40
    พันธ์
    0.40
    Imm
    0.39
    ။
    0.39
    Mu
    0.38
    BindView
    0.38
    Prop
    0.37
    Activations Density 0.000%

    No Known Activations