© 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. 64098
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    ︹
    0.39
     डाल
    0.38
    금
    0.38
    Purple
    0.38
    Arch
    0.38
    lockSeconds
    0.37
     Aero
    0.37
     lich
    0.37
    Arrows
    0.37
     आख
    0.36
    POSITIVE LOGITS
     తొ
    0.45
    стье
    0.41
    Ⲏ
    0.41
     Rabbi
    0.40
     Tú
    0.39
    UST
    0.38
     Sexuality
    0.37
    堰
    0.37
     অতঃ
    0.37
    usti
    0.37
    Activations Density 0.000%

    No Known Activations