© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166563
    Prev
    Next
    INDEX
    Explanations

    Post

    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_56_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
    करता
    0.41
    Requirement
    0.40
    ላለ
    0.39
     Requirement
    0.38
    ")->
    0.37
    торой
    0.36
     Req
    0.36
     reps
    0.36
     Params
    0.35
     anta
    0.35
    POSITIVE LOGITS
    inv
    0.36
    luss
    0.36
    show
    0.35
     Myr
    0.35
    indul
    0.34
    onavir
    0.34
    滤
    0.34
    posting
    0.33
    par
    0.33
    chr
    0.33
    Activations Density 0.000%

    No Known Activations