© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145291
    Prev
    Next
    INDEX
    Explanations

    sales cycles and figures

    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_0_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
    t
    2.05
    a
    1.91
    ;
    1.88
    g
    1.84
    e
    1.81
    :
    1.80
    the
    1.76
    >
    1.72
    /
    1.64
    an
    1.63
    POSITIVE LOGITS
     complicaciones
    1.44
    ל
    1.42
     ماشینونه
    1.40
    ла
    1.33
     canciones
    1.31
    رځ
    1.31
    Е
    1.30
    ್ರ
    1.28
     ganancias
    1.25
     году
    1.24
    Activations Density 0.001%

    No Known Activations