© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33458
    Prev
    Next
    INDEX
    Explanations

    chalk

    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
    anfa
    0.47
     olive
    0.46
    ويب
    0.43
    Olive
    0.43
     Oliver
    0.43
     Olive
    0.43
     OL
    0.42
    榄
    0.41
     Publish
    0.40
    muy
    0.38
    POSITIVE LOGITS
     Chalk
    0.55
     Halk
    0.49
    Cast
    0.45
     chalk
    0.44
    chalk
    0.44
     kast
    0.43
     Hox
    0.42
     Hok
    0.41
    刻
    0.41
    Kor
    0.40
    Activations Density 0.022%

    No Known Activations