© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18812
    Prev
    Next
    INDEX
    Explanations

    directional and spatial descriptions

    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_15_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
    ts
    0.53
    iki
    0.52
    z
    0.50
    st
    0.50
    ls
    0.49
    atique
    0.49
    sted
    0.48
    k
    0.48
    akes
    0.47
    ha
    0.47
    POSITIVE LOGITS
     portavoz
    0.59
     polvo
    0.56
     или
    0.56
     semana
    0.55
     maxn
    0.55
    ུ
    0.55
     demiş
    0.54
    ARROW
    0.54
    нил
    0.53
    IFIED
    0.53
    Activations Density 0.019%

    No Known Activations