© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97246
    Prev
    Next
    INDEX
    Explanations

    parenthetical text and commands

    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_14_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
    decrease
    0.50
     inverter
    0.50
     distractions
    0.49
     distract
    0.47
    도
    0.47
    시간
    0.46
     curls
    0.46
     cài
    0.46
    IActions
    0.46
     endorph
    0.46
    POSITIVE LOGITS
    孰
    0.47
    ियों
    0.46
    ghis
    0.46
    ancen
    0.45
    ਛ
    0.43
     Epp
    0.42
    ἦ
    0.42
    ας
    0.42
     विश्वास
    0.42
    詩
    0.42
    Activations Density 0.000%

    No Known Activations