© 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. 46501
    Prev
    Next
    INDEX
    Explanations

    linked 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_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
     प्रत
    0.49
    ﺍ
    0.49
     ஏற்படுத்துகிறது
    0.47
     لاہور
    0.47
    처럼
    0.46
    लपुर
    0.46
    L
    0.46
     Dealers
    0.46
     ऑन
    0.45
     پنجاب
    0.45
    POSITIVE LOGITS
     as
    0.58
     didn
    0.55
    嵬
    0.54
     calmer
    0.54
    om
    0.52
    inę
    0.52
    émi
    0.51
     frustrations
    0.50
     safer
    0.50
     halted
    0.50
    Activations Density 0.001%

    No Known Activations