© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159561
    Prev
    Next
    INDEX
    Explanations

    intermedial prefixes

    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_2_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
    ل
    1.25
    ↵
    1.17
    in
    1.17
    ac
    1.08
    لي
    1.07
    و
    1.05
    res
    1.03
    ল
    1.02
    កំព
    1.01
    3
    0.98
    POSITIVE LOGITS
    ى
    1.27
    к
    1.25
    ני
    1.20
    ای
    1.17
    די
    1.16
    .",
    1.15
    נו
    1.15
    ı
    1.13
    માં
    1.12
     animale
    1.11
    Activations Density 0.000%

    No Known Activations