© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6010
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or state

    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
    mead
    0.42
     setting
    0.39
    Setting
    0.36
    ="{{
    0.36
    ̍
    0.36
     Setting
    0.36
    ्थ
    0.36
     Pupils
    0.35
    ο
    0.35
     ตั้ง
    0.35
    POSITIVE LOGITS
     lugares
    0.48
     места
    0.46
     場所
    0.43
    場所
    0.43
     място
    0.43
     plek
    0.42
     mjest
    0.42
     dv
    0.42
    곳
    0.42
     mest
    0.41
    Activations Density 0.010%

    No Known Activations