© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199536
    Prev
    Next
    INDEX
    Explanations

    speech, recognition, emphasis, ID, implementation, thin, shoes

    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_9_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
    iffent
    0.61
    би
    0.54
    وٹی
    0.54
    टाइम
    0.54
    𝚞
    0.53
     уеннары
    0.52
     alegr
    0.52
    addena
    0.52
    asında
    0.52
    <unused696>
    0.52
    POSITIVE LOGITS
     at
    0.46
     by
    0.45
     Wood
    0.43
     complained
    0.42
     por
    0.42
     to
    0.42
     ID
    0.41
    ్య
    0.41
    por
    0.40
     leg
    0.40
    Activations Density 0.000%

    No Known Activations