© 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. 45431
    Prev
    Next
    INDEX
    Explanations

    **signifier and signified**

    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
     Inserting
    0.52
     grudnia
    0.51
    箒
    0.50
    ூல்
    0.48
     Strikes
    0.47
     Página
    0.47
     Flyers
    0.47
     Seek
    0.46
     Ship
    0.46
     Bilbao
    0.46
    POSITIVE LOGITS
     worsening
    0.48
    Status
    0.46
     actief
    0.44
     toprak
    0.42
     milling
    0.42
    C
    0.42
     اشرف
    0.42
    _(
    0.41
     adamant
    0.41
     brass
    0.41
    Activations Density 0.001%

    No Known Activations