© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7169
    Prev
    Next
    INDEX
    Explanations

    activation of BRAF V600E

    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_39_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
     REACTORS
    0.43
     eficiencia
    0.41
    贖
    0.41
     gobierno
    0.40
     коопера
    0.40
     energías
    0.38
     jangan
    0.38
     hearers
    0.38
    涮
    0.38
     نقصان
    0.38
    POSITIVE LOGITS
    TC
    0.41
     அறு
    0.39
     chirp
    0.39
    CrossRef
    0.39
    chir
    0.38
    Im
    0.37
     dysfunction
    0.36
    wann
    0.35
    им
    0.35
    lid
    0.34
    Activations Density 0.002%

    No Known Activations