© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157719
    Prev
    Next
    INDEX
    Explanations

    makers

    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_2_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
    IT
    1.14
    AT
    1.06
    ing
    1.05
     I
    1.03
    ES
    1.02
    .
    0.98
    AG
    0.97
    ۰
    0.95
    ANS
    0.93
    AKE
    0.91
    POSITIVE LOGITS
    م
    1.36
    د
    1.34
    س
    1.31
    ه
    1.30
    ب
    1.29
    _
    1.16
    كان
    1.08
    on
    1.06
    <0x0D>
    1.05
    an
    1.05
    Activations Density 0.000%

    No Known Activations