© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23263
    Prev
    Next
    INDEX
    Explanations

    Att

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    rata
    0.38
     durum
    0.37
    equity
    0.36
    埤
    0.36
    ევე
    0.35
     ডাক
    0.35
    भूति
    0.34
     걸
    0.34
     Anas
    0.34
    CUIT
    0.34
    POSITIVE LOGITS
     att
    0.55
    ro
    0.53
    roon
    0.44
    しまいました
    0.38
    rául
    0.38
    ിക്കുന്നത്
    0.36
    estly
    0.34
     penyakit
    0.34
     extracellular
    0.34
    Physics
    0.33
    Activations Density 0.002%

    No Known Activations