© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132346
    Prev
    Next
    INDEX
    Explanations

    custom + noun/suffix

    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_1_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
     be
    0.91
    IB
    0.89
    be
    0.87
    ſ
    0.87
    هِ
    0.86
    থেষ্ট
    0.78
    bevel
    0.77
    vo
    0.77
    ke
    0.75
    IAN
    0.75
    POSITIVE LOGITS
    자
    1.25
    ্য
    1.09
    ار
    1.08
    사
    1.07
    тся
    1.01
    א
    1.00
    々は
    0.95
    িয়া
    0.94
    સ
    0.92
    ש
    0.92
    Activations Density 0.001%

    No Known Activations