© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174506
    Prev
    Next
    INDEX
    Explanations

    event dates and turns

    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_20_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
     approx
    0.44
     Zw
    0.43
     Approx
    0.42
     Approximately
    0.41
     approximately
    0.39
    rophiles
    0.36
     Schw
    0.36
    2
    0.35
     roughly
    0.35
     Euch
    0.34
    POSITIVE LOGITS
    र्नर
    0.46
    Into
    0.44
    醎
    0.44
    ursal
    0.41
     versiones
    0.40
    ipzig
    0.40
     акысыз
    0.40
     dönem
    0.39
    үүн
    0.39
    Versions
    0.38
    Activations Density 0.000%

    No Known Activations