© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36334
    Prev
    Next
    INDEX
    Explanations

    specific entities and events

    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_50_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
    মুখী
    0.40
     Nase
    0.39
    상을
    0.39
     Naras
    0.38
     N
    0.38
    Norman
    0.37
     Mao
    0.37
     m
    0.37
    वार
    0.37
     Nand
    0.37
    POSITIVE LOGITS
     الاس
    0.39
    డ
    0.39
    deserialize
    0.38
    ql
    0.38
    apanicola
    0.38
     dejan
    0.37
    丹
    0.37
     Godwin
    0.37
    廝
    0.37
    annotations
    0.37
    Activations Density 0.000%

    No Known Activations