© 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. 199958
    Prev
    Next
    INDEX
    Explanations

    named entities or code

    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
     S
    0.85
     الس
    0.59
    S
    0.56
     s
    0.48
     הס
    0.48
     સ
    0.47
     E
    0.47
     С
    0.46
     Georgetown
    0.45
     Sylvia
    0.44
    POSITIVE LOGITS
    Leg
    0.40
    som
    0.39
    Som
    0.39
    ച്ചി
    0.39
     البل
    0.38
     Dele
    0.38
     Bleu
    0.38
    LGBT
    0.37
    Somebody
    0.37
     Somebody
    0.36
    Activations Density 0.020%

    No Known Activations