© 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. 171661
    Prev
    Next
    INDEX
    Explanations

    copyright violations and terms of service

    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
     dez
    0.45
    وك
    0.45
    תי
    0.45
    стри
    0.43
    bikes
    0.43
    }
    0.43
    вал
    0.43
    は
    0.42
     nig
    0.42
    骓
    0.42
    POSITIVE LOGITS
     uncovering
    0.47
     maximizing
    0.46
     Investigative
    0.45
     utmost
    0.44
     whom
    0.44
     بالای
    0.43
     elevating
    0.42
    Между
    0.41
     Hague
    0.41
     सौंपा
    0.40
    Activations Density 0.000%

    No Known Activations