© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150724
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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_59_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
    वाती
    0.42
     %>.
    0.42
    пки
    0.40
     endExpNow
    0.39
     தொகை
    0.39
    ContextHeader
    0.38
    তই
    0.38
    خته
    0.37
    竿
    0.37
    }}$;
    0.37
    POSITIVE LOGITS
    About
    0.54
     occured
    0.50
     fit
    0.50
    Nach
    0.50
     about
    0.49
     happened
    0.47
     occurred
    0.47
     he
    0.46
    发生了
    0.46
     came
    0.45
    Activations Density 0.005%

    No Known Activations