© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245910
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
     callbacks
    0.60
     speculate
    0.58
    .“
    0.58
    callbacks
    0.56
     annotate
    0.56
    ഃ
    0.56
     พร้อม
    0.56
     subscribe
    0.55
     appeals
    0.55
     Appellate
    0.55
    POSITIVE LOGITS
    표
    0.49
    셔
    0.48
    }]
    0.47
    군
    0.45
    दर्
    0.44
    Display
    0.44
    Teller
    0.42
     otvore
    0.41
    ያ
    0.41
    Fil
    0.41
    Activations Density 0.000%

    No Known Activations