© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50915
    Prev
    Next
    INDEX
    Explanations

    status

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     rejo
    0.38
     human
    0.36
    Instrument
    0.35
    Compile
    0.35
    fns
    0.35
     reins
    0.35
     instrument
    0.33
     재
    0.33
     kred
    0.33
    strings
    0.33
    POSITIVE LOGITS
    드리
    0.43
     فراہم
    0.43
    ವು
    0.42
    <unused86>
    0.41
     алы
    0.39
     குழந்தைகளின்
    0.39
    <unused34>
    0.39
     REQUEST
    0.39
     데이터를
    0.38
    писание
    0.38
    Activations Density 0.001%

    No Known Activations