© 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. 63662
    Prev
    Next
    INDEX
    Explanations

    lasers and light

    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
     చెప్పు
    0.41
    rmap
    0.37
    齿
    0.37
     mic
    0.37
    opath
    0.36
     રૂપ
    0.36
    右手
    0.36
    манов
    0.35
    ုပ်
    0.35
     заключения
    0.35
    POSITIVE LOGITS
    argin
    0.40
     saf
    0.40
     testimony
    0.40
     High
    0.40
    HAPPY
    0.40
     ULTRA
    0.37
     Saf
    0.37
    }/${
    0.37
     приходится
    0.36
     pInBuffer
    0.36
    Activations Density 0.001%

    No Known Activations