© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204707
    Prev
    Next
    INDEX
    Explanations

    style and className attributes

    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_25_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
     ਭ
    0.44
    ҳ
    0.44
    Mo
    0.44
    VK
    0.41
     기능을
    0.41
     мо
    0.40
    API
    0.40
    VPN
    0.40
     ɖ
    0.40
     गुजरात
    0.40
    POSITIVE LOGITS
     seinen
    0.38
     redonde
    0.37
     Costello
    0.36
     aflat
    0.36
     terceiro
    0.35
     Johns
    0.35
    脚注
    0.35
     Castello
    0.35
    જના
    0.35
     tatsächlich
    0.34
    Activations Density 0.000%

    No Known Activations