© 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. 78640
    Prev
    Next
    INDEX
    Explanations

    file operations or directory checks

    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
    ENCY
    0.41
     IBA
    0.41
     I
    0.40
    bestroute
    0.37
    ද්ධ
    0.36
     i
    0.35
     beneficiary
    0.35
     Í
    0.35
    𝐼
    0.34
     enda
    0.34
    POSITIVE LOGITS
    üman
    0.36
    Continue
    0.35
     rece
    0.34
     Continue
    0.34
     হ্
    0.33
     tamper
    0.32
    kult
    0.32
     Takah
    0.32
    unning
    0.32
    吉
    0.32
    Activations Density 0.020%

    No Known Activations