© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134200
    Prev
    Next
    INDEX
    Explanations

    hardware wallets

    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_1_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
     in
    1.45
     be
    1.27
    를
    1.18
     conceivably
    1.15
    도
    1.10
    на
    1.08
    S
    1.08
    U
    1.08
     در
    1.05
    이지만
    1.05
    POSITIVE LOGITS
    1
    1.66
    2
    1.63
    3
    1.48
    6
    1.36
    7
    1.34
    4
    1.31
    9
    1.31
    ل
    1.28
    ر
    1.19
    ל
    1.17
    Activations Density 0.000%

    No Known Activations