© 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. 144822
    Prev
    Next
    INDEX
    Explanations

    constituents

    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
    ן
    1.64
    า
    1.63
    ก
    1.62
    다
    1.59
    ט
    1.55
    ડ
    1.55
    ות
    1.45
    ми
    1.44
    정
    1.41
    ла
    1.40
    POSITIVE LOGITS
     be
    1.38
    offs
    1.13
     реб
    1.12
    be
    1.10
    ur
    1.08
    v
    1.08
     (
    1.07
    erin
    1.07
    inars
    1.05
    für
    1.04
    Activations Density 0.000%

    No Known Activations