© 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. 79330
    Prev
    Next
    INDEX
    Explanations

    imp- words

    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
    س
    1.63
    <0x80>
    1.45
    的
    1.36
     and
    1.24
    ка
    1.22
    ের
    1.14
    شي
    1.14
    та
    1.13
    ς
    1.13
    ري
    1.12
    POSITIVE LOGITS
    an
    1.43
    ان
    1.36
    a
    1.31
    l
    1.31
     for
    1.30
    .
    1.16
    ه
    1.09
     this
    1.03
     the
    1.02
    p
    1.02
    Activations Density 0.000%

    No Known Activations