© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210656
    Prev
    Next
    INDEX
    Explanations

    content knowledge and delivery

    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_20_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
    iado
    0.48
    linien
    0.47
    <unused2150>
    0.45
     utama
    0.44
     auspicious
    0.43
    ämä
    0.43
     προβ
    0.42
     efficacious
    0.42
    禎
    0.41
    ंसा
    0.40
    POSITIVE LOGITS
    Manu
    0.46
    Russian
    0.44
    transpose
    0.44
    Landscape
    0.42
    Settings
    0.41
    SUR
    0.41
    cx
    0.40
    XT
    0.40
    Ident
    0.40
    Carry
    0.40
    Activations Density 0.001%

    No Known Activations