© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3393
    Prev
    Next
    INDEX
    Explanations

    movement verbs followed by direction

    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_39_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
    ğrafl
    0.44
    Dé
    0.40
    MouseClicked
    0.39
     इंग्लैंड
    0.38
     レザー
    0.37
    Depart
    0.36
    सँग
    0.36
    ḍ
    0.36
    England
    0.35
    冫
    0.35
    POSITIVE LOGITS
     Weights
    0.42
     Clown
    0.41
     Anti
    0.41
    cata
    0.41
     Moments
    0.40
     Marked
    0.40
     Katie
    0.40
     task
    0.39
     Roses
    0.38
     Logic
    0.38
    Activations Density 0.048%

    No Known Activations