© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131159
    Prev
    Next
    INDEX
    Explanations

    Fukushima, Hokkaido, Nagasaki

    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_1_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
    ل
    1.63
    p
    1.32
    le
    1.20
    il
    1.10
    да
    1.08
    z
    1.05
    k
    1.04
    ق
    1.04
    x
    1.01
    les
    0.99
    POSITIVE LOGITS
     avaient
    1.30
     evaluar
    1.21
     allemand
    1.16
     postérieurs
    1.12
     acides
    1.12
     aplatis
    1.11
     organiques
    1.10
    ु
    1.10
     économiques
    1.07
     augmenter
    1.06
    Activations Density 0.001%

    No Known Activations