© 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. 159838
    Prev
    Next
    INDEX
    Explanations

    psn, config, username, password

    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
    ة
    1.22
    د
    1.20
    在
    1.17
    ing
    1.10
     in
    1.10
    ۰
    1.06
    िंग
    1.01
    ography
    1.01
    被
    0.98
    ০
    0.97
    POSITIVE LOGITS
     a
    1.34
    м
    1.33
    ک
    1.17
    _
    1.13
    ש
    1.12
    й
    1.10
    IA
    1.04
    𝘤
    1.01
    ளைஞ
    0.98
     gadis
    0.98
    Activations Density 0.000%

    No Known Activations