© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179414
    Prev
    Next
    INDEX
    Explanations

    colors following 'and'

    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
     Kiz
    0.40
     einfach
    0.40
    只
    0.39
     elevates
    0.39
     accidents
    0.39
    ❸
    0.38
     Dauer
    0.38
     Maks
    0.37
    могою
    0.37
     litigants
    0.37
    POSITIVE LOGITS
     マルチ
    0.43
    exponential
    0.43
    eta
    0.42
    esquerda
    0.40
    journ
    0.39
     примеру
    0.38
    slash
    0.38
    פא
    0.38
    德
    0.37
    cargar
    0.37
    Activations Density 0.003%

    No Known Activations