© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43138
    Prev
    Next
    INDEX
    Explanations

    links to articles

    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_22_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
    Launcher
    0.45
    ISATION
    0.43
     exempel
    0.40
    Repo
    0.40
     рестора
    0.40
    可
    0.39
     propulsion
    0.39
    WAN
    0.38
    ToAction
    0.37
    霽
    0.37
    POSITIVE LOGITS
     अभिने
    0.40
     අතර
    0.39
     थोड़ा
    0.39
     خیلی
    0.38
    Σ
    0.38
     backside
    0.38
     चयनित
    0.38
    die
    0.38
     boon
    0.38
     इत्यादि
    0.38
    Activations Density 0.001%

    No Known Activations