© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41554
    Prev
    Next
    INDEX
    Explanations

    user input and accounts

    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_22_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
    wor
    0.26
    uffer
    0.24
    </b>
    0.23
    raits
    0.23
    ref
    0.23
    oms
    0.23
    afi
    0.22
    irk
    0.22
    j
    0.21
    inv
    0.21
    POSITIVE LOGITS
     chicago
    0.27
     Первая
    0.24
     Dublin
    0.23
    ږد
    0.23
     Chicago
    0.22
    関西
    0.22
    ritas
    0.22
    racting
    0.22
     elementName
    0.22
     الاولى
    0.22
    Activations Density 0.018%

    No Known Activations