© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39797
    Prev
    Next
    INDEX
    Explanations

    colors

    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_57_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
     red
    0.79
    red
    0.65
    红
    0.51
     Red
    0.45
    Red
    0.44
    紅
    0.40
     interview
    0.40
    interview
    0.39
     红
    0.38
     tan
    0.37
    POSITIVE LOGITS
     negro
    1.27
    Neg
    1.23
     verde
    1.21
     Verde
    1.20
     Negro
    1.19
     Blanc
    1.18
     neg
    1.16
     blanc
    1.16
     rouge
    1.15
     Blanco
    1.15
    Activations Density 0.025%

    No Known Activations