© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46363
    Prev
    Next
    INDEX
    Explanations

    Ser with RNA/gas

    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_3_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
    ة
    0.68
    ă
    0.68
    ing
    0.64
    ्लो
    0.63
    utum
    0.63
    imble
    0.62
    kowe
    0.62
    間
    0.59
    kj
    0.59
    kari
    0.59
    POSITIVE LOGITS
    1.06
    </b>
    0.70
    <0x0D>
    0.66
    is
    0.64
    ش
    0.63
    না
    0.62
     secteur
    0.61
     степень
    0.61
     déchets
    0.60
     boissons
    0.59
    Activations Density 0.000%

    No Known Activations