© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151729
    Prev
    Next
    INDEX
    Explanations

    colour

    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_60_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
    宜
    0.70
     bør
    0.59
     deber
    0.57
     следует
    0.57
     Should
    0.51
     należy
    0.51
     Amongst
    0.49
     Whilst
    0.46
     слід
    0.45
     dever
    0.42
    POSITIVE LOGITS
    な
    0.75
     colour
    0.68
    Colour
    0.55
    colour
    0.55
     color
    0.53
    これ
    0.53
     colours
    0.53
    colours
    0.51
    カラー
    0.50
     colouring
    0.50
    Activations Density 0.000%

    No Known Activations