© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    models. or AX

    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
    ’,
    0.16
    es
    0.14
    quele
    0.14
    ’.
    0.14
    un
    0.13
    ,’”
    0.13
    </h3>
    0.12
    ്‍
    0.12
    <0xB6>
    0.12
     Hals
    0.12
    POSITIVE LOGITS
    s
    0.17
     відпо
    0.14
     bimod
    0.14
    vox
    0.13
    ítő
    0.13
    Ꮟ
    0.13
     손
    0.13
     sambil
    0.13
     paradigms
    0.13
     ها
    0.13
    Activations Density 0.120%

    No Known Activations