© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 81470
    Prev
    Next
    INDEX
    Explanations

    NA, NApiVersion

    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
    '
    1.96
    ０
    1.45
    l
    1.32
    "
    1.23
    ‘
    1.23
    lık
    1.16
    '<
    1.13
    jší
    1.10
    َ
    1.06
    "<
    1.05
    POSITIVE LOGITS
    an
    2.09
    ا
    2.00
    as
    1.84
    .
    1.84
    2
    1.84
    า
    1.77
    ла
    1.77
    ة
    1.77
    ing
    1.76
    ले
    1.68
    Activations Density 0.001%

    No Known Activations