© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60595
    Prev
    Next
    INDEX
    Explanations

    phrase ending

    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_2_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
    ض
    1.19
    st
    0.99
    .
    0.98
    set
    0.94
    sc
    0.93
    dam
    0.90
    icken
    0.88
    dings
    0.88
    ored
    0.88
    ci
    0.86
    POSITIVE LOGITS
    ي
    1.27
     marc
    1.02
     recordar
    0.98
     peinture
    0.98
     clic
    0.97
    ле
    0.96
    不會
    0.96
    ㅋㅋ
    0.95
     réponses
    0.95
     resolv
    0.95
    Activations Density 0.005%

    No Known Activations