© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162518
    Prev
    Next
    INDEX
    Explanations

    or tomorrow

    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
    s
    2.83
    t
    1.79
    r
    1.68
    ی
    1.63
    re
    1.60
    y
    1.56
    ים
    1.55
    ک
    1.51
    g
    1.43
    to
    1.40
    POSITIVE LOGITS
    )
    1.80
    }
    1.48
    O
    1.42
    >
    1.42
    '
    1.41
    <
    1.36
    E
    1.34
    P
    1.33
    {
    1.32
    1.26
    Activations Density 0.000%

    No Known Activations