© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10964
    Prev
    Next
    INDEX
    Explanations

    Save: Save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     Aga
    0.41
    "%>
    0.39
    oyne
    0.38
    }]},
    0.38
    pann
    0.38
     എന്നീ
    0.38
    "})
    0.37
     NAP
    0.37
     saved
    0.36
    "}
    0.36
    POSITIVE LOGITS
     definition
    0.50
     definición
    0.42
     डेफिनेशन
    0.40
     defines
    0.39
     Definition
    0.38
     rare
    0.38
     परिभाषा
    0.37
    genc
    0.37
    definition
    0.35
     определение
    0.35
    Activations Density 0.002%

    No Known Activations