© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205921
    Prev
    Next
    INDEX
    Explanations

    content

    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_56_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
     like
    0.82
    Like
    0.73
     Like
    0.73
     مثل
    0.69
     seperti
    0.68
    like
    0.65
     LIKE
    0.63
    如
    0.60
    เช่น
    0.59
     như
    0.59
    POSITIVE LOGITS
     consistent
    0.54
    consistent
    0.42
     fairly
    0.40
    Consistent
    0.38
    MyToolkit
    0.38
    াঃ
    0.36
     distinguishes
    0.36
    ΟΣ
    0.36
     ਖ
    0.35
    jskich
    0.35
    Activations Density 0.013%

    No Known Activations