© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175768
    Prev
    Next
    INDEX
    Explanations

    tamarind paste

    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
    /
    0.51
    +
    0.49
     +
    0.45
    রকম
    0.44
    ബൈ
    0.43
    ISBN
    0.41
    Spirit
    0.40
    Ә
    0.40
    UPDATE
    0.39
    ப்பதி
    0.39
    POSITIVE LOGITS
     anta
    0.55
     tournaments
    0.52
     comenzó
    0.51
     Dispon
    0.50
     dollars
    0.49
     anything
    0.48
     hare
    0.48
     bedeut
    0.48
     została
    0.48
     pedra
    0.48
    Activations Density 0.000%

    No Known Activations