© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46451
    Prev
    Next
    INDEX
    Explanations

    free will

    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_13_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
    has
    0.19
    k
    0.19
    a
    0.18
    z
    0.18
    am
    0.17
    task
    0.16
    haben
    0.16
    </b>
    0.16
    ch
    0.16
    in
    0.15
    POSITIVE LOGITS
    🕖
    0.20
     sinuses
    0.19
     hypothalamus
    0.18
    ◽
    0.17
     lundi
    0.17
     निजामाच्या
    0.17
     कॉनकॉर्ड
    0.17
     ombil
    0.17
     pince
    0.17
    тика
    0.16
    Activations Density 0.005%

    No Known Activations