© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103219
    Prev
    Next
    INDEX
    Explanations

    COUNT(DISTINCT

    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_1_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
    ول
    1.37
    ע
    1.24
    なんか
    1.20
    ن
    1.20
    z
    1.17
    inov
    1.16
    ل
    1.16
    िन
    1.14
    jg
    1.13
    ἲ
    1.12
    POSITIVE LOGITS
     in
    1.65
    在
    1.32
     be
    1.28
    ও
    1.23
    s
    1.21
    :
    1.13
    ς
    1.06
     I
    1.05
    <0xB9>
    1.03
    도
    1.01
    Activations Density 0.001%

    No Known Activations