© 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. 58026
    Prev
    Next
    INDEX
    Explanations

    Josh names

    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
     правило
    0.40
    ราช
    0.40
     желание
    0.39
    독
    0.38
     свое
    0.37
     viewer
    0.37
    KLC
    0.37
    Բ
    0.37
    𝘽
    0.37
     топ
    0.37
    POSITIVE LOGITS
    upi
    0.43
    entra
    0.42
    enture
    0.41
    esta
    0.38
    endem
    0.38
    chis
    0.37
    ’
    0.37
    util
    0.37
    περι
    0.37
    urers
    0.36
    Activations Density 0.000%

    No Known Activations