© 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. 145169
    Prev
    Next
    INDEX
    Explanations

    start of string or exponentiation

    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
    :
    1.16
    )…
    0.89
    са
    0.88
    )
    0.86
    ಸ್ಕೊ
    0.82
    ት
    0.79
     teeming
    0.78
     minivan
    0.78
     sesión
    0.77
    )”.
    0.77
    POSITIVE LOGITS
     of
    1.15
    ian
    0.93
     (
    0.89
    ld
    0.88
    p
    0.87
    r
    0.86
    ler
    0.86
    df
    0.86
    den
    0.84
    v
    0.81
    Activations Density 0.003%

    No Known Activations