© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11823
    Prev
    Next
    INDEX
    Explanations

    rescue

    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
     Ciências
    0.39
    銷
    0.36
     Science
    0.36
     కాల్
    0.36
    交代
    0.35
     Ciência
    0.35
    緘
    0.35
     science
    0.34
     साइंस
    0.34
     Hud
    0.34
    POSITIVE LOGITS
     rescue
    2.55
     rescued
    2.38
    Rescue
    2.33
     Rescue
    2.28
     rescues
    2.28
    rescue
    2.22
     rescuing
    2.22
    救
    1.91
     rescat
    1.90
     rescu
    1.79
    Activations Density 0.060%

    No Known Activations