© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29617
    Prev
    Next
    INDEX
    Explanations

    team needs to rebuild or extend

    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_40_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
     powerhouse
    0.37
     fuertes
    0.35
     Biological
    0.35
     fortes
    0.34
    強
    0.33
     pick
    0.32
    pick
    0.32
    chad
    0.32
     picks
    0.32
     strong
    0.31
    POSITIVE LOGITS
     Panam
    0.36
     $\{(
    0.35
     Akar
    0.35
     পাঁ
    0.35
     receta
    0.35
     ngũ
    0.33
    organizzazione
    0.33
    हित्य
    0.33
     villains
    0.33
     organizacji
    0.33
    Activations Density 0.004%

    No Known Activations