© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172560
    Prev
    Next
    INDEX
    Explanations

    the bottom number

    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_20_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
     continuity
    0.44
     ቅ
    0.44
     portrayal
    0.42
     የእ
    0.41
     پیک
    0.40
     配
    0.40
     Pius
    0.39
     equity
    0.38
     உண்மைய
    0.38
     नि
    0.38
    POSITIVE LOGITS
    нера
    0.40
     monedas
    0.38
    ذي
    0.38
     số
    0.38
     hamburgers
    0.37
    凰
    0.37
     suminist
    0.35
     membeli
    0.35
     diversos
    0.34
    মুখি
    0.34
    Activations Density 0.000%

    No Known Activations