© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166994
    Prev
    Next
    INDEX
    Explanations

    lists with "and"

    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_31_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
    ،
    0.46
    、
    0.43
    含む
    0.41
    !,
    0.40
    %、
    0.40
    ™,
    0.40
    ²,
    0.39
    ፣
    0.39
     ፣
    0.39
     {},
    0.39
    POSITIVE LOGITS
    GroupID
    0.38
     sekaligus
    0.37
     শেল
    0.37
     минуту
    0.36
    <unused85>
    0.35
    glColor
    0.35
    <unused31>
    0.35
    glazed
    0.35
    实力
    0.34
    rogate
    0.33
    Activations Density 0.046%

    No Known Activations