© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48593
    Prev
    Next
    INDEX
    Explanations

    with each

    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
     happened
    0.35
     pronouncing
    0.33
     Aurang
    0.32
    有効
    0.31
    剷
    0.31
    רה
    0.31
     Happened
    0.31
     getattr
    0.31
    خراج
    0.30
    たる
    0.30
    POSITIVE LOGITS
     respekt
    0.35
     què
    0.35
     جگہ
    0.34
    脐
    0.33
    jectives
    0.32
     ڈویل
    0.32
     tie
    0.32
    Toe
    0.32
    txtarea
    0.32
    ns
    0.31
    Activations Density 0.002%

    No Known Activations