© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 78305
    Prev
    Next
    INDEX
    Explanations

    can you identify

    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_31_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
     بیا
    0.42
     ears
    0.39
     Ears
    0.39
     artefacts
    0.38
    뽐
    0.38
    沇
    0.38
     rarer
    0.38
    ान्
    0.37
    脖
    0.36
     eyes
    0.36
    POSITIVE LOGITS
     Apollo
    0.40
    機械
    0.39
    Apollo
    0.38
     ME
    0.38
    ndash
    0.37
     compart
    0.36
    Option
    0.36
    folds
    0.36
     futuros
    0.35
     actomyosin
    0.35
    Activations Density 0.001%

    No Known Activations