© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60793
    Prev
    Next
    INDEX
    Explanations

    Teachable, seas

    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_2_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
    v
    0.79
    n
    0.76
    st
    0.73
    ер
    0.66
    sa
    0.64
    sk
    0.63
    vär
    0.61
    s
    0.61
    ين
    0.60
    )
    0.60
    POSITIVE LOGITS
    ك
    0.67
    주
    0.64
    ف
    0.60
    <0x0D>
    0.59
    \,.
    0.59
    \,\
    0.56
    이었다
    0.54
    Sum
    0.53
    साठी
    0.53
    А
    0.52
    Activations Density 0.000%

    No Known Activations