© 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. 150494
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Antique
    0.40
    <0xC2>
    0.40
     Exotic
    0.39
    สาม
    0.36
    }}
    0.35
    곁
    0.35
     EI
    0.35
    પ
    0.34
     Processing
    0.33
     Lattice
    0.33
    POSITIVE LOGITS
    )**
    0.47
    MANN
    0.44
    )$\\
    0.42
     rufis
    0.40
    )】
    0.39
    )}$,
    0.39
    awn
    0.38
    lowercase
    0.38
    anche
    0.38
    )/(
    0.37
    Activations Density 0.002%

    No Known Activations