© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32133
    Prev
    Next
    INDEX
    Explanations

    desire or willingness to

    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_7_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
    2
    0.73
    ق
    0.61
     granit
    0.59
     actuator
    0.59
    ง
    0.58
     macarons
    0.57
     callus
    0.57
     bitcoins
    0.56
    ว
    0.55
     देशमुख
    0.55
    POSITIVE LOGITS
     Opportunities
    0.64
     Someone
    0.59
    ressed
    0.59
     Celebrating
    0.57
     Learning
    0.56
     Implications
    0.55
     }_{
    0.54
    ্সে
    0.54
    ut
    0.54
     Relationships
    0.53
    Activations Density 0.162%

    No Known Activations