© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50866
    Prev
    Next
    INDEX
    Explanations

    URLs ending in closing parenthesis

    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_10_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
    0.52
     to
    0.46
    лення
    0.45
     for
    0.42
    n
    0.42
    س
    0.41
    r
    0.40
    nach
    0.40
    sp
    0.38
    қ
    0.38
    POSITIVE LOGITS
    ).
    0.49
    </strong>
    0.41
    )
    0.40
    aa
    0.38
    ని
    0.35
    .
    0.35
    ي
    0.35
    </b>
    0.35
    มัน
    0.34
     Aquinas
    0.34
    Activations Density 0.008%

    No Known Activations