© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203160
    Prev
    Next
    INDEX
    Explanations

    currency codes or abbreviations

    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_6_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
     be
    0.54
     to
    0.52
    ص
    0.47
     and
    0.47
    ב
    0.46
     el
    0.43
     savoir
    0.41
     at
    0.41
     was
    0.41
     raisons
    0.41
    POSITIVE LOGITS
    l
    0.47
    g
    0.44
    ni
    0.43
    km
    0.42
    name
    0.42
    metic
    0.42
    mination
    0.42
    da
    0.41
     Tattha
    0.41
    storey
    0.40
    Activations Density 0.000%

    No Known Activations