© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60712
    Prev
    Next
    INDEX
    Explanations

    连线 (connect line)

    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_11_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
    У
    0.68
     funzione
    0.66
     stesso
    0.63
    matically
    0.61
    foration
    0.60
    structures
    0.58
     محور
    0.58
    center
    0.57
    驱动
    0.57
     acht
    0.56
    POSITIVE LOGITS
     Kib
    0.64
     Isi
    0.63
    筱
    0.58
     shrimps
    0.56
     Kis
    0.56
     weeding
    0.54
     Tiki
    0.54
    ί
    0.54
     Frédéric
    0.53
     Ched
    0.53
    Activations Density 0.000%

    No Known Activations