© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89870
    Prev
    Next
    INDEX
    Explanations

    wanderer / words ending in er

    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_3_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
    ፩
    0.67
     сучас
    0.62
     yaklaşık
    0.57
     काफी
    0.56
    ใช้
    0.56
    єдна
    0.56
    哪些
    0.55
     wodurch
    0.55
    ್
    0.55
     двох
    0.55
    POSITIVE LOGITS
    ang
    0.88
    ،
    0.88
    link
    0.77
    、
    0.70
    TO
    0.69
    PA
    0.68
    ong
    0.66
    ition
    0.65
    IO
    0.65
    wood
    0.64
    Activations Density 0.000%

    No Known Activations