© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194640
    Prev
    Next
    INDEX
    Explanations

    VFI, Hit Parade, SupertrendMFIStrategy

    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_4_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
    >$
    0.19
    >
    0.19
    0.18
    ０
    0.18
     reassuring
    0.18
    ู
    0.17
     bắt
    0.17
     souten
    0.17
     on
    0.17
    。
    0.17
    POSITIVE LOGITS
    p
    0.37
    n
    0.33
    t
    0.31
    v
    0.31
    se
    0.26
    st
    0.26
    that
    0.25
    g
    0.25
    b
    0.25
    k
    0.24
    Activations Density 0.003%

    No Known Activations