© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88955
    Prev
    Next
    INDEX
    Explanations

    Kansas-Nebraska

    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_3_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
    ல்
    0.80
    kim
    0.73
    ى
    0.70
    da
    0.70
     विकार
    0.64
    ।
    0.63
    ։
    0.63
    directions
    0.62
    et
    0.61
    任何
    0.61
    POSITIVE LOGITS
    علي
    0.70
     I
    0.61
    ח
    0.60
     RSVP
    0.59
     envoyer
    0.59
     reinforce
    0.59
            
    0.58
     étape
    0.58
    小便
    0.58
    <unused2172>
    0.57
    Activations Density 0.002%

    No Known Activations