© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138612
    Prev
    Next
    INDEX
    Explanations

    beautiful

    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_12_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
    ਣਾ
    0.31
    俣
    0.26
     Atra
    0.24
     Normalmente
    0.23
    тена
    0.23
    잍
    0.23
     випадку
    0.23
    зора
    0.23
     Veamos
    0.22
    числя
    0.21
    POSITIVE LOGITS
    s
    0.35
    c
    0.29
    de
    0.27
    hd
    0.27
    sc
    0.26
    sm
    0.25
    hur
    0.25
    ho
    0.25
    ab
    0.24
    d
    0.24
    Activations Density 0.000%

    No Known Activations