© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65627
    Prev
    Next
    INDEX
    Explanations

    regex and code parsing

    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_46_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
     separa
    0.43
     chiffre
    0.41
    Wallace
    0.41
    鈣
    0.39
    ៈ
    0.39
    یتے
    0.38
    Carta
    0.38
    เลข
    0.38
    ∼
    0.37
    حدى
    0.37
    POSITIVE LOGITS
     Red
    0.42
     People
    0.41
    braith
    0.40
    .(\
    0.37
    ?\
    0.37
     Reduced
    0.37
     (?
    0.37
     (?,
    0.36
    炽
    0.36
    ियां
    0.36
    Activations Density 0.008%

    No Known Activations