© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16783
    Prev
    Next
    INDEX
    Explanations

    URL mapping and routing

    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_15_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
     nocturnal
    0.53
     s
    0.52
     han
    0.52
     h
    0.51
     x
    0.49
     zero
    0.49
     \
    0.48
     m
    0.48
     ferm
    0.48
     zároveň
    0.48
    POSITIVE LOGITS
     শ্রীযুক্ত
    0.58
    commentaire
    0.54
     umíst
    0.54
    Sheikh
    0.53
     Ashraf
    0.53
     භාවිත
    0.52
     रिश्
    0.51
    wym
    0.51
     ಅಂಶ
    0.51
     பயன்படுத்து
    0.50
    Activations Density 0.001%

    No Known Activations