© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104902
    Prev
    Next
    INDEX
    Explanations

    treatment of conditions

    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_1_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
    I
    1.26
    D
    1.23
    4
    1.21
    ²
    1.14
    L
    1.12
    8
    1.09
    ،
    1.06
    9
    1.05
    سال
    1.02
    다
    1.02
    POSITIVE LOGITS
    elijke
    1.03
     viele
    1.02
     caratteristiche
    0.99
     HAS
    0.98
     I
    0.96
     cinco
    0.95
     ovog
    0.94
    ной
    0.94
     excelente
    0.94
     moyenne
    0.93
    Activations Density 0.000%

    No Known Activations