© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61427
    Prev
    Next
    INDEX
    Explanations

    hexadecimal data or strings

    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_11_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
    F
    0.50
    פ
    0.48
    ]，
    0.47
     Raise
    0.46
    ंग
    0.46
    FUTURE
    0.46
    חיל
    0.45
    Shower
    0.44
    Bottle
    0.44
    Rocks
    0.44
    POSITIVE LOGITS
    etin
    0.51
     lov
    0.51
    のア
    0.50
    itable
    0.49
    esign
    0.49
     ovo
    0.48
     laboris
    0.48
    ᓃ
    0.48
    ia
    0.47
    onk
    0.47
    Activations Density 0.026%

    No Known Activations