© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17369
    Prev
    Next
    INDEX
    Explanations

    multipart/form-data, body, fields, nonce

    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_15_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
     snow
    0.31
    D
    0.30
     So
    0.28
     că
    0.27
     SO
    0.27
     Dec
    0.26
     September
    0.26
     December
    0.26
     Knox
    0.26
    ന്ദ
    0.26
    POSITIVE LOGITS
    validated
    0.35
    iqui
    0.33
     የበለጠ
    0.32
    వారి
    0.31
    ಿಸಿದ್ದ
    0.31
     ጭ
    0.31
    ੦
    0.31
     ګرځنده
    0.31
    gypte
    0.31
    upl
    0.30
    Activations Density 0.037%

    No Known Activations