© 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. 195694
    Prev
    Next
    INDEX
    Explanations

    fictional narratives

    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
    arios
    0.40
     ث
    0.40
     insisted
    0.40
     reserved
    0.39
    eron
    0.39
     Rc
    0.38
     refined
    0.38
     સે
    0.38
     Fax
    0.38
     insist
    0.38
    POSITIVE LOGITS
     LUT
    0.41
    潁
    0.38
    undur
    0.38
    ভারতে
    0.37
     NOK
    0.37
    伊
    0.37
    Graphic
    0.37
    둣
    0.37
    קב
    0.36
    gouv
    0.35
    Activations Density 0.000%

    No Known Activations