© 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. 58457
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Le
    0.45
    Indigo
    0.44
    decl
    0.40
    spe
    0.40
    भोग
    0.39
    ಸ್ಥ
    0.39
    Decl
    0.39
    >[]
    0.39
    酆
    0.38
    蜓
    0.37
    POSITIVE LOGITS
    ("|
    0.46
    <b>
    0.45
    .”)
    0.44
     व्हाट
    0.44
    ⁸
    0.43
    .).
    0.43
    .)
    0.41
    .
    0.41
    ."""
    0.41
     mula
    0.41
    Activations Density 0.004%

    No Known Activations