© 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. 63159
    Prev
    Next
    INDEX
    Explanations

    Res

    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
    earing
    0.39
    reflectionMap
    0.39
     fonbet
    0.38
    꼈
    0.37
     droplets
    0.36
     bowlers
    0.36
     inactiv
    0.36
    enza
    0.36
    чной
    0.36
    чная
    0.36
    POSITIVE LOGITS
     y
    0.42
    veli
    0.39
     prow
    0.37
     a
    0.36
    Ӯ
    0.34
    nesses
    0.34
     иденти
    0.34
    ror
    0.34
    Vel
    0.34
    ാർ
    0.34
    Activations Density 0.000%

    No Known Activations