© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195686
    Prev
    Next
    INDEX
    Explanations

    two followed by noun

    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_4_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
    v
    0.37
    druck
    0.34
    ুগত্য
    0.31
    dokument
    0.31
    nova
    0.29
    textview
    0.29
    guard
    0.28
    steel
    0.28
    bogen
    0.28
    h
    0.28
    POSITIVE LOGITS
    in
    0.49
    و
    0.45
    ী
    0.45
    िंग
    0.45
    ות
    0.44
    ă
    0.42
    ą
    0.41
    ę
    0.39
    ון
    0.39
    ون
    0.39
    Activations Density 0.004%

    No Known Activations