© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209112
    Prev
    Next
    INDEX
    Explanations

    tracking standard

    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_25_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
    लू
    0.46
    olph
    0.44
     disagreeable
    0.43
    ल
    0.43
    ेल
    0.42
     subscrib
    0.42
    ेट
    0.41
     Vek
    0.41
    ўні
    0.41
     vett
    0.41
    POSITIVE LOGITS
     Comparing
    0.45
     상
    0.45
     Analyzing
    0.43
    しましょう
    0.42
     Surreal
    0.42
    したが
    0.42
     하여
    0.41
    하여
    0.40
     можливо
    0.40
     Specialties
    0.40
    Activations Density 0.000%

    No Known Activations