© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201991
    Prev
    Next
    INDEX
    Explanations

    email subjects

    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_46_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
    Computing
    0.43
    অর্থ
    0.41
    Could
    0.41
    could
    0.40
    “-
    0.40
    Check
    0.39
    যায়
    0.39
    screenshots
    0.39
     обрабо
    0.38
    No
    0.38
    POSITIVE LOGITS
    itmen
    0.44
    呟
    0.39
     figli
    0.39
    𒈨
    0.39
     empecé
    0.37
    શ્મી
    0.37
    ataka
    0.36
    ხმარ
    0.36
     hijos
    0.35
    ום
    0.35
    Activations Density 0.003%

    No Known Activations