© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219146
    Prev
    Next
    INDEX
    Explanations

    red error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    覽
    0.41
    <{},
    0.39
    ：“
    0.38
    वाँ
    0.38
    DidEnter
    0.37
    "।
    0.37
    AsUp
    0.36
    jsxFileName
    0.36
     టై
    0.36
     함
    0.35
    POSITIVE LOGITS
    спо
    0.41
    getValue
    0.36
     correctional
    0.36
    cyte
    0.35
     scandalous
    0.35
     corners
    0.35
     oef
    0.34
    showerror
    0.34
     atomic
    0.34
    懺
    0.34
    Activations Density 0.001%

    No Known Activations