© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194642
    Prev
    Next
    INDEX
    Explanations

    fills with dread or pleasure

    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_15_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
    ഗം
    0.53
    좋
    0.53
     다양한
    0.52
     buenas
    0.51
    弾
    0.51
    మీ
    0.50
    зня
    0.50
    Medico
    0.50
     Good
    0.49
     migrant
    0.49
    POSITIVE LOGITS
     deliberate
    0.57
    antic
    0.55
    ()}
    0.52
    ats
    0.51
     fingern
    0.50
    st
    0.50
    antu
    0.50
    linestyle
    0.49
    ણા
    0.47
    ^{*}}\
    0.47
    Activations Density 0.003%

    No Known Activations