© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142617
    Prev
    Next
    INDEX
    Explanations

    Neurosama, Edison, dfs

    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_0_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
    '
    2.20
    ه
    2.13
    ا
    2.08
    ה
    2.06
    다
    2.02
    a
    1.94
    ’
    1.94
    dır
    1.85
    an
    1.84
     can
    1.80
    POSITIVE LOGITS
    的感觉
    1.15
    1.12
    ER
    1.09
    的设计
    1.09
     viktig
    1.08
     postcode
    1.08
    的产品
    1.07
     toon
    1.03
    rop
    1.01
    的光
    0.99
    Activations Density 0.000%

    No Known Activations