© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31223
    Prev
    Next
    INDEX
    Explanations

    William Henry Harrison, Ringo Starr, Huxley

    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_31_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
    デュー
    0.37
    ኺ
    0.37
    ңү
    0.35
    qa
    0.34
    Iraq
    0.32
    qc
    0.32
    duck
    0.32
    NaBH
    0.32
    nM
    0.31
    ቧ
    0.31
    POSITIVE LOGITS
     വിദ്യാ
    0.42
     카드
    0.35
     indist
    0.34
     गाँ
    0.31
    ষ্টা
    0.31
    ల్యే
    0.31
     bhas
    0.31
     病
    0.31
    病
    0.31
     গো
    0.31
    Activations Density 0.002%

    No Known Activations