© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241403
    Prev
    Next
    INDEX
    Explanations

    Blue Grass Boys

    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_25_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
     взаимодей
    0.41
    或
    0.40
     RESON
    0.38
     hoặc
    0.38
    нтип
    0.38
     supple
    0.37
     &/
    0.36
     lieve
    0.36
    🧛
    0.36
    мно
    0.35
    POSITIVE LOGITS
     Dur
    0.48
     Johnson
    0.47
     Star
    0.45
     Ade
    0.45
     Treasures
    0.44
     Initial
    0.43
     S
    0.43
     Central
    0.43
     Need
    0.43
     Exit
    0.43
    Activations Density 0.000%

    No Known Activations