© 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
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99779
    Prev
    Next
    INDEX
    Explanations

    settlement process

    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_14_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
    )+(
    0.12
     Mound
    0.11
     Incluso
    0.11
    )+
    0.11
    +
    0.10
     chl
    0.10
    ?)
    0.10
     Februar
    0.10
    ﹔
    0.10
    ?」
    0.10
    POSITIVE LOGITS
    लीवुड
    0.11
    two
    0.11
    ката
    0.11
     in
    0.10
    lene
    0.10
    kosten
    0.10
    cano
    0.10
    不需要
    0.10
    torch
    0.10
     LIE
    0.10
    Activations Density 0.005%

    No Known Activations