© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121135
    Prev
    Next
    INDEX
    Explanations

    let's say you

    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_38_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
     görür
    0.37
     በኋላ
    0.37
     Allowed
    0.37
     Giveen
    0.36
     シュ
    0.36
    ']),
    0.36
     overboard
    0.35
     beobachten
    0.35
     Crash
    0.35
     viendo
    0.35
    POSITIVE LOGITS
    niej
    0.38
    ΕΙ
    0.37
    涿
    0.37
    ἦ
    0.37
    endi
    0.36
     denomin
    0.36
     melting
    0.36
     හැ
    0.36
    魅
    0.35
    Acts
    0.34
    Activations Density 0.006%

    No Known Activations