© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165151
    Prev
    Next
    INDEX
    Explanations

    geographical locations and water bodies

    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_13_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
    on
    0.34
    j
    0.32
    sp
    0.32
    st
    0.32
    strong
    0.31
    deceased
    0.31
    a
    0.31
    n
    0.30
    ed
    0.30
     Perspective
    0.29
    POSITIVE LOGITS
     dafür
    0.31
    郆
    0.29
     wetter
    0.28
    󠁥
    0.28
     krä
    0.28
     rück
    0.28
    ęć
    0.28
    íte
    0.27
     पड़
    0.27
    ią
    0.27
    Activations Density 0.002%

    No Known Activations