© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90215
    Prev
    Next
    INDEX
    Explanations

    Important

    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_60_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
    :
    0.67
     :
    0.42
    best
    0.40
    ：
    0.38
    )=
    0.37
     best
    0.35
    ério
    0.35
    över
    0.35
    +
    0.34
    attutto
    0.34
    POSITIVE LOGITS
     considerations
    1.30
     Considerations
    1.17
     consideration
    1.11
     Consideration
    0.90
     고려
    0.77
     considerazione
    0.70
     consideración
    0.70
    考虑
    0.68
    考慮
    0.61
    ↵↵
    0.59
    Activations Density 0.013%

    No Known Activations