© 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. 220621
    Prev
    Next
    INDEX
    Explanations

    return values

    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
     Grundlagen
    0.33
    薹
    0.33
     Akad
    0.33
    にした
    0.33
     сфор
    0.33
     queue
    0.33
     camshaft
    0.33
     đẩy
    0.32
     queuing
    0.32
     queued
    0.32
    POSITIVE LOGITS
    daten
    0.34
    🚶
    0.34
     שנה
    0.33
    urney
    0.32
     gour
    0.32
    ew
    0.32
    pentine
    0.31
    clerosis
    0.31
    აპ
    0.31
     راجس
    0.31
    Activations Density 0.002%

    No Known Activations