© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38981
    Prev
    Next
    INDEX
    Explanations

    overwriting or writing

    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_3_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
    D
    1.26
    P
    1.23
    R
    1.20
    C
    1.17
    F
    1.14
    H
    1.13
    S
    1.01
    E
    1.00
    B
    0.99
    X
    0.98
    POSITIVE LOGITS
    ların
    0.62
    0.60
     तत्
    0.56
    fifo
    0.55
    soldiers
    0.54
    лись
    0.54
    shit
    0.53
    いです
    0.53
    sklär
    0.53
    si
    0.52
    Activations Density 0.009%

    No Known Activations