© 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. 57688
    Prev
    Next
    INDEX
    Explanations

    to develop, to deliver, to compare, to list

    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
     limo
    0.72
    డీపీ
    0.61
    $>
    0.60
    ђено
    0.59
     turbulent
    0.59
    underwear
    0.58
    🙏🏻
    0.58
    𝒑
    0.58
    Img
    0.58
     nerveux
    0.58
    POSITIVE LOGITS
    ون
    0.73
     A
    0.64
    t
    0.63
    ou
    0.58
     as
    0.58
    ها
    0.57
     ord
    0.57
    艾
    0.56
    said
    0.56
     ACTIV
    0.55
    Activations Density 0.001%

    No Known Activations