© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108461
    Prev
    Next
    INDEX
    Explanations

    service descriptions

    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_1_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
    1
    1.13
    0
    1.06
     for
    1.02
    PART
    1.00
    pr
    0.98
     *)
    0.98
    Don
    0.96
    parser
    0.93
    Theorem
    0.92
    H
    0.92
    POSITIVE LOGITS
    いた
    1.56
     doesn
    1.52
    ان
    1.48
     wasn
    1.41
     aujourd
    1.40
    𝒆
    1.37
     didn
    1.36
     isn
    1.36
    ABILITIES
    1.36
     Trotsky
    1.35
    Activations Density 0.005%

    No Known Activations