© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101264
    Prev
    Next
    INDEX
    Explanations

    HitFilm Express

    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_16_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
    resham
    0.61
    ຽ
    0.55
    IoT
    0.55
     autonomía
    0.53
    Primera
    0.50
     inkjet
    0.50
    墨
    0.50
    εια
    0.49
    ASER
    0.49
    setSelected
    0.49
    POSITIVE LOGITS
    ж
    0.59
     flung
    0.55
     outbursts
    0.55
     o
    0.54
    d
    0.53
     MISS
    0.52
    ي
    0.52
     Louis
    0.52
     M
    0.51
     outburst
    0.49
    Activations Density 0.000%

    No Known Activations