© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1733
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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
     또
    0.41
    もう
    0.38
    Clos
    0.38
    Cas
    0.38
     আরেকটি
    0.38
    อีก
    0.37
    ulat
    0.36
    Another
    0.35
    봐
    0.35
    Carbon
    0.35
    POSITIVE LOGITS
     consequence
    0.72
     consequently
    0.70
     Consequently
    0.67
    Consequently
    0.64
     conséquence
    0.59
     like
    0.58
     consecuencia
    0.58
     result
    0.57
     consequent
    0.55
     conseguenza
    0.54
    Activations Density 0.023%

    No Known Activations