© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62302
    Prev
    Next
    INDEX
    Explanations

    AZ

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    s
    0.63
    va
    0.59
    uv
    0.55
    ga
    0.54
    za
    0.54
    na
    0.53
    iv
    0.53
    sa
    0.51
    sk
    0.51
    amos
    0.51
    POSITIVE LOGITS
    RW
    0.61
    RZ
    0.61
    RIP
    0.60
    RIM
    0.60
    RIS
    0.60
    RIG
    0.59
    RID
    0.57
    RICAL
    0.57
    RIN
    0.57
    RAL
    0.55
    Activations Density 0.000%

    No Known Activations