© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52196
    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_55_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
    Rhe
    0.41
    pore
    0.39
    Calcium
    0.39
     बालो
    0.38
    谯
    0.38
    濂
    0.37
    gust
    0.37
    胼
    0.36
    蓯
    0.35
    elliptic
    0.35
    POSITIVE LOGITS
     blue
    0.74
     black
    0.60
     green
    0.59
     red
    0.59
     white
    0.59
     gray
    0.57
     grey
    0.57
     bluish
    0.54
     bleu
    0.52
    blue
    0.51
    Activations Density 0.010%

    No Known Activations