© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37477
    Prev
    Next
    INDEX
    Explanations

    risk, relief, trials

    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
     huéspedes
    0.68
    ت
    0.68
    юй
    0.66
     téléphon
    0.63
     meriye
    0.63
     compres
    0.63
    ക്കൂ
    0.63
     зараз
    0.62
    <unused82>
    0.61
     recib
    0.61
    POSITIVE LOGITS
    A
    0.87
     (
    0.83
     A
    0.72
     G
    0.67
    O
    0.67
     for
    0.65
     S
    0.65
     been
    0.64
    ar
    0.61
    ↵↵
    0.61
    Activations Density 0.010%

    No Known Activations