© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211965
    Prev
    Next
    INDEX
    Explanations

    plays a role

    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_19_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
    rme
    0.38
    ppes
    0.37
    rbara
    0.37
    iggio
    0.36
    holt
    0.36
     =\
    0.36
     Patients
    0.35
    Argentina
    0.35
    red
    0.34
    relli
    0.34
    POSITIVE LOGITS
     superfluid
    0.35
    腺
    0.35
     quaternary
    0.34
     aden
    0.34
     transistor
    0.34
     समर्
    0.33
     epinephrine
    0.33
     supremely
    0.33
     bail
    0.33
     alphan
    0.33
    Activations Density 0.022%

    No Known Activations