© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81484
    Prev
    Next
    INDEX
    Explanations

    play or playful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ama
    1.28
    I
    1.26
    L
    1.10
    ui
    1.09
    มัน
    1.07
    ።
    1.06
    ни
    1.05
    ς
    1.05
    uz
    1.03
    azione
    1.02
    POSITIVE LOGITS
    a
    1.90
    ه
    1.74
    u
    1.70
    та
    1.63
    i
    1.53
    ר
    1.45
    er
    1.43
    ي
    1.42
    AN
    1.40
    ir
    1.38
    Activations Density 0.002%

    No Known Activations