© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171147
    Prev
    Next
    INDEX
    Explanations

    'x' followed by 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_20_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
    ᇂ
    0.28
     Headlines
    0.27
     headlines
    0.27
    ᓕ
    0.26
     κόσ
    0.26
     dedu
    0.26
     τελευτα
    0.26
    മിതി
    0.26
     unes
    0.26
     eyepiece
    0.26
    POSITIVE LOGITS
    si
    0.28
    лот
    0.27
    Berg
    0.26
     разработан
    0.26
    bio
    0.26
    bergs
    0.26
    铮
    0.26
    重的
    0.25
     Berg
    0.25
     இருப்பதாக
    0.25
    Activations Density 0.006%

    No Known Activations