© 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. 175114
    Prev
    Next
    INDEX
    Explanations

    direction and destination

    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
    的中
    0.48
     xã
    0.47
     зві
    0.44
    گو
    0.44
     Superhero
    0.44
    お
    0.43
     Preliminary
    0.43
     gesellschaft
    0.42
     സോഷ്യ
    0.42
     Folklore
    0.40
    POSITIVE LOGITS
     `.
    0.48
     corn
    0.45
    icen
    0.45
     '.'
    0.44
    ​.
    0.44
    vVertex
    0.44
    screen
    0.43
     olives
    0.42
    vred
    0.42
    input
    0.42
    Activations Density 0.000%

    No Known Activations