© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32184
    Prev
    Next
    INDEX
    Explanations

    color 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_50_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
     Shir
    0.46
    Shir
    0.45
    ens
    0.43
    Leb
    0.43
    Shr
    0.41
    फे
    0.40
    ⑥
    0.40
    lb
    0.40
    Brun
    0.39
     পরিপূর্ণ
    0.39
    POSITIVE LOGITS
     Move
    0.48
     CRE
    0.47
     màu
    0.44
     Colour
    0.43
     MEDIA
    0.42
     무료
    0.42
     हिटलर
    0.42
     colour
    0.41
     color
    0.41
    Move
    0.40
    Activations Density 0.025%

    No Known Activations