© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209679
    Prev
    Next
    INDEX
    Explanations

    poets and authors

    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_20_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
     fase
    0.45
     nakon
    0.44
     Memorial
    0.43
    uting
    0.42
     cláss
    0.42
     dangere
    0.42
     memorial
    0.41
     V
    0.41
     tif
    0.41
     ainda
    0.40
    POSITIVE LOGITS
    சை
    0.43
     যতটা
    0.43
    尽量
    0.42
    oprotein
    0.42
    بیداری
    0.42
     använder
    0.42
    pays
    0.42
    Onset
    0.42
     tăng
    0.41
    équilibre
    0.41
    Activations Density 0.000%

    No Known Activations