© 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. 138391
    Prev
    Next
    INDEX
    Explanations

    Fix

    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
     pap
    0.44
     prompted
    0.41
     prompting
    0.39
    醸
    0.39
     tone
    0.38
     induced
    0.38
     pathogenicity
    0.38
    摺
    0.38
    )|^
    0.38
    回應
    0.36
    POSITIVE LOGITS
    Fail
    0.42
     Liver
    0.41
    Liver
    0.40
     Story
    0.40
     corrupt
    0.39
     તર
    0.39
    umps
    0.39
    文章
    0.39
     sg
    0.39
    Errors
    0.39
    Activations Density 0.002%

    No Known Activations