© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38636
    Prev
    Next
    INDEX
    Explanations

    Disclaimer

    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_57_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
    JUD
    0.37
    ゃ
    0.37
     }}$,
    0.36
    ERR
    0.36
    PROBLE
    0.36
     meadow
    0.35
    ALLOC
    0.35
    tty
    0.34
    )}}
    0.34
    Ambient
    0.34
    POSITIVE LOGITS
     GTA
    0.42
     cep
    0.42
     jod
    0.38
    visory
    0.37
     Це
    0.37
    ecuzione
    0.37
     facts
    0.37
     सम्
    0.37
     Ψ
    0.37
     cest
    0.36
    Activations Density 0.001%

    No Known Activations