© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29137
    Prev
    Next
    INDEX
    Explanations

    front-line fighters

    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_10_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
     for
    0.29
    1
    0.28
    8
    0.28
    OP
    0.26
     For
    0.25
     validar
    0.25
    ם
    0.24
    3
    0.24
    何
    0.23
     servizi
    0.22
    POSITIVE LOGITS
    bies
    0.27
    ulates
    0.25
     automakers
    0.24
    ctions
    0.24
     américains
    0.23
    𝓭
    0.23
     ecologists
    0.23
     insectes
    0.23
    acies
    0.23
    inians
    0.23
    Activations Density 0.006%

    No Known Activations