© 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. 63653
    Prev
    Next
    INDEX
    Explanations

    Hal

    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
    Possible
    0.42
    itles
    0.40
    ශ්‍ය
    0.39
     possible
    0.38
    eleration
    0.38
     \$
    0.38
     নিষ
    0.38
    anced
    0.37
     rotation
    0.36
    One
    0.36
    POSITIVE LOGITS
    Hal
    0.71
     Hal
    0.66
     halogen
    0.63
     hal
    0.61
     HAL
    0.57
    halogen
    0.53
     halide
    0.51
    hal
    0.50
    鹵
    0.50
     halides
    0.48
    Activations Density 0.002%

    No Known Activations