© 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. 9857
    Prev
    Next
    INDEX
    Explanations

    eye movements; figure eight; EMDR

    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
    Beschreibung
    0.29
     प्रसंस्करण
    0.29
    ൊരു
    0.28
    煤
    0.27
     Após
    0.25
    未来
    0.25
     कां
    0.25
    akuza
    0.25
     appass
    0.25
    ぁ
    0.25
    POSITIVE LOGITS
    uvres
    0.28
     ('
    0.28
    '.
    0.27
    idina
    0.27
     sakta
    0.27
     Sayles
    0.27
    ‟
    0.27
     (\"
    0.27
     ERK
    0.27
     escap
    0.26
    Activations Density 0.004%

    No Known Activations