© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91049
    Prev
    Next
    INDEX
    Explanations

    "Vibe" and punctuation

    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
    be
    0.71
    то
    0.66
    p
    0.66
    to
    0.65
    ne
    0.58
    co
    0.58
    on
    0.55
    berg
    0.53
    owy
    0.52
    we
    0.51
    POSITIVE LOGITS
     எனக்கு
    0.54
     VIA
    0.54
     YA
    0.53
     aut
    0.52
     авто
    0.52
     comuni
    0.51
     Ā
    0.51
    сынын
    0.51
     autó
    0.50
     dakkh
    0.50
    Activations Density 0.069%

    No Known Activations