© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59095
    Prev
    Next
    INDEX
    Explanations

    split, splits, splitting

    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
    .
    1.55
    8
    1.36
    on
    1.33
    ला
    1.28
    9
    1.27
    ong
    1.24
    4
    1.20
    r
    1.16
    the
    1.14
    7
    1.13
    POSITIVE LOGITS
    ة
    1.83
    a
    1.45
    ية
    1.22
    ду
    1.16
    ă
    1.14
    פר
    1.13
    1.13
    هي
    1.12
    ও
    1.06
    ה
    1.06
    Activations Density 0.000%

    No Known Activations