© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175692
    Prev
    Next
    INDEX
    Explanations

    separates `: `

    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_24_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
     hardness
    0.41
     ось
    0.39
     Biografie
    0.38
    ッジ
    0.37
    metals
    0.36
    லாமல்
    0.36
    銖
    0.35
    ciones
    0.35
    walle
    0.35
     réflexion
    0.35
    POSITIVE LOGITS
     যারা
    0.44
     इनकी
    0.41
    seid
    0.40
    &$
    0.40
     وقف
    0.39
    이자
    0.38
     예측
    0.38
     EIR
    0.37
    ISK
    0.36
     তারা
    0.36
    Activations Density 0.003%

    No Known Activations