© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1952
    Prev
    Next
    INDEX
    Explanations

    | or control sequences

    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_39_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
    Bath
    0.53
    bath
    0.51
     bath
    0.50
     baths
    0.48
    浴
    0.47
     Baths
    0.46
     Bath
    0.43
    Tet
    0.40
    बह
    0.40
    Batch
    0.39
    POSITIVE LOGITS
     fidelity
    0.40
    ሲ
    0.39
     state
    0.38
     빠른
    0.38
     PHIL
    0.38
     গ্রন্থে
    0.37
     realizations
    0.37
    ccin
    0.37
     preparation
    0.36
     Steering
    0.36
    Activations Density 0.056%

    No Known Activations