© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193470
    Prev
    Next
    INDEX
    Explanations

    over / aside / open / away

    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_4_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
    ார்
    0.64
    <0x81>
    0.57
    ائح
    0.55
    ல்
    0.52
    o
    0.51
    萂
    0.51
     Giveen
    0.50
    ൽ
    0.50
    <0x93>
    0.50
    ன்ஸ்
    0.49
    POSITIVE LOGITS
    .
    0.95
    ก
    0.79
    0.75
    '
    0.62
    ב
    0.61
    е
    0.60
    I
    0.58
    ED
    0.57
    um
    0.57
    한
    0.53
    Activations Density 0.067%

    No Known Activations