© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40598
    Prev
    Next
    INDEX
    Explanations

    prepositions linking concepts

    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_11_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
    كتور
    0.42
    ل
    0.40
     teint
    0.38
     bibliothèque
    0.37
    гом
    0.37
    ス
    0.36
     câble
    0.36
    нской
    0.36
    ється
    0.36
    к
    0.36
    POSITIVE LOGITS
    ’
    0.47
    ad
    0.38
     P
    0.37
    out
    0.37
     A
    0.36
     agreement
    0.35
    ase
    0.35
    ලි
    0.35
    ros
    0.34
     ok
    0.34
    Activations Density 0.057%

    No Known Activations