© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80465
    Prev
    Next
    INDEX
    Explanations

    future

    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
    in
    1.76
    ak
    1.59
    ↵
    1.58
     for
    1.53
    d
    1.48
    q
    1.45
    al
    1.40
    ch
    1.34
    t
    1.34
    am
    1.33
    POSITIVE LOGITS
     músculos
    1.33
     cả
    1.30
     físicos
    1.30
     enzimas
    1.27
    ва
    1.26
     válv
    1.25
     व
    1.23
     ομά
    1.23
     tratados
    1.21
     tecnológicas
    1.21
    Activations Density 0.004%

    No Known Activations