© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35999
    Prev
    Next
    INDEX
    Explanations

    select or align environment

    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_11_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
    </h2>
    0.61
     a
    0.59
    <start_of_image>
    0.57
     <
    0.55
     Envelope
    0.54
    AN
    0.52
    IN
    0.51
    izophren
    0.50
     Aspergillus
    0.50
    <
    0.50
    POSITIVE LOGITS
    мо
    0.76
    ные
    0.69
     técnica
    0.67
    čių
    0.67
    𝗻
    0.64
    hér
    0.63
    боры
    0.63
    ту
    0.61
    ał
    0.61
    τούν
    0.60
    Activations Density 0.005%

    No Known Activations