© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61790
    Prev
    Next
    INDEX
    Explanations

    I

    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
    OJ
    0.63
    AJ
    0.61
    OM
    0.58
    OR
    0.55
    Ο
    0.54
    ES
    0.54
    US
    0.53
    OY
    0.53
    IM
    0.53
    HA
    0.51
    POSITIVE LOGITS
     repeat
    0.53
     REQUIREMENTS
    0.50
     OBJECT
    0.49
     ST
    0.48
     APPRO
    0.48
     TABLE
    0.48
     FIGURE
    0.48
     QUESTIONS
    0.47
     NAMES
    0.47
     RULES
    0.47
    Activations Density 0.001%

    No Known Activations