© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5102
    Prev
    Next
    INDEX
    Explanations

    traits

    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_44_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
    läger
    0.42
    dinger
    0.39
    upné
    0.38
    &&(
    0.37
    ঙ
    0.36
     drum
    0.35
    তেন
    0.35
    tuned
    0.35
    ::-
    0.35
    guided
    0.34
    POSITIVE LOGITS
     trait
    3.03
     traits
    2.75
    trait
    2.70
    Trait
    2.69
     Traits
    2.61
    traits
    2.52
    Traits
    2.47
     Tra
    1.84
     TRA
    1.63
    Tra
    1.59
    Activations Density 0.073%

    No Known Activations