© 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. 207834
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     T
    0.60
     тө
    0.39
     Т
    0.38
     lay
    0.37
     тә
    0.37
    flake
    0.36
    唇
    0.36
    block
    0.35
     Lump
    0.35
     Sud
    0.34
    POSITIVE LOGITS
    मिया
    0.42
     бумаги
    0.42
     कागज
    0.42
     کاغذ
    0.40
     paper
    0.40
    ellschaft
    0.39
    ษา
    0.39
     بہانہ
    0.39
    纸
    0.38
    WB
    0.37
    Activations Density 0.000%

    No Known Activations