© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203105
    Prev
    Next
    INDEX
    Explanations

    echo

    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
    чительно
    0.40
    直
    0.40
     arh
    0.39
    ".$
    0.37
     கண
    0.36
    休息
    0.36
    typename
    0.35
    负责人
    0.35
     babel
    0.35
     gerçekten
    0.34
    POSITIVE LOGITS
     সাম্প্র
    0.43
    hawks
    0.42
     Heart
    0.42
     scorpion
    0.41
    㐹
    0.41
    Heart
    0.41
     vanligt
    0.40
     dq
    0.40
     كث
    0.40
    󠁣
    0.40
    Activations Density 0.000%

    No Known Activations