© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54633
    Prev
    Next
    INDEX
    Explanations

    most

    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
    ोगी
    0.41
     رش
    0.40
    衔
    0.40
     factorization
    0.39
    lied
    0.39
    raisal
    0.39
    銜
    0.39
    引领
    0.38
    ression
    0.37
    inputValue
    0.37
    POSITIVE LOGITS
     prat
    0.40
     Durable
    0.39
     sevent
    0.37
     सभ
    0.37
    ｍ
    0.37
     reappear
    0.36
    ваемые
    0.36
     Nbd
    0.35
     мелдеш
    0.35
     Δ
    0.35
    Activations Density 0.001%

    No Known Activations