© 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. 80568
    Prev
    Next
    INDEX
    Explanations

    Packard, Packing

    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
    ت
    1.64
    to
    1.43
    یم
    1.34
    .
    1.28
    ня
    1.27
    یک
    1.22
    دی
    1.22
    می
    1.19
    the
    1.18
    وم
    1.18
    POSITIVE LOGITS
    ir
    1.73
    ال
    1.65
    ين
    1.59
    يب
    1.43
    ח
    1.41
    ar
    1.35
    al
    1.29
    ent
    1.27
    لية
    1.26
    الك
    1.26
    Activations Density 0.001%

    No Known Activations