© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216909
    Prev
    Next
    INDEX
    Explanations

    kids and children learning and needing

    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_31_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
     impatiently
    0.39
    lette
    0.38
    aide
    0.38
     ajud
    0.38
    }$.,
    0.37
     impatient
    0.37
    )}$,
    0.36
     couch
    0.35
    ProductImages
    0.35
    +}$
    0.35
    POSITIVE LOGITS
    ानंद
    0.38
     контро
    0.38
     रोजिक
    0.38
     requiring
    0.37
     컨트롤
    0.37
     sepat
    0.37
     economies
    0.36
    ैट
    0.35
    контро
    0.35
     stores
    0.34
    Activations Density 0.003%

    No Known Activations