© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46146
    Prev
    Next
    INDEX
    Explanations

    idea of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    ค
    0.63
    s
    0.61
     б
    0.60
    ים
    0.57
     December
    0.54
     encryption
    0.50
     highest
    0.49
    ിലാ
    0.49
     decrypt
    0.49
     builder
    0.48
    POSITIVE LOGITS
    ρο
    0.51
    гун
    0.50
    铛
    0.50
     Zahlen
    0.49
    gebras
    0.48
    esthetics
    0.47
    anel
    0.47
    en
    0.47
     abstractions
    0.47
    ezing
    0.46
    Activations Density 0.007%

    No Known Activations