© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120731
    Prev
    Next
    INDEX
    Explanations

    miscalculation

    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_38_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
    ászló
    0.41
    䒠
    0.41
    歹
    0.40
     Eno
    0.40
     Passed
    0.38
     drips
    0.38
     desenvol
    0.38
    stricken
    0.38
    Ծ
    0.38
     giocando
    0.38
    POSITIVE LOGITS
     Athenian
    0.59
     Athens
    0.52
     Athenians
    0.50
    Athens
    0.50
     Pel
    0.46
    Pel
    0.43
     classical
    0.43
     Pelican
    0.40
    ATH
    0.39
     pel
    0.39
    Activations Density 0.023%

    No Known Activations