© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9096
    Prev
    Next
    INDEX
    Explanations

    sea ice

    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_13_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
    .*
    0.11
     *
    0.11
    l
    0.11
    rians
    0.10
    rizona
    0.10
     år
    0.10
    rl
    0.10
    6
    0.10
    arians
    0.09
    are
    0.09
    POSITIVE LOGITS
    ك
    0.11
    ম
    0.10
    ي
    0.10
    ಕ
    0.10
    המ
    0.10
    ከ
    0.09
     éta
    0.09
     objectivity
    0.09
     परे
    0.09
     অবস্থ
    0.09
    Activations Density 0.016%

    No Known Activations