© 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. 210464
    Prev
    Next
    INDEX
    Explanations

    services for consumers or clients

    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
     this
    0.40
     lied
    0.36
     هذا
    0.35
     meandering
    0.34
     a
    0.34
    es
    0.33
    自己
    0.31
     an
    0.31
    ":
    0.30
     д
    0.30
    POSITIVE LOGITS
    ත්‍
    0.35
     –,
    0.35
    éré
    0.34
    últ
    0.34
     alimentaires
    0.34
    ॅप
    0.34
     posljed
    0.34
     acompañada
    0.34
     últimas
    0.33
    咦
    0.33
    Activations Density 0.002%

    No Known Activations