© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34847
    Prev
    Next
    INDEX
    Explanations

    un/une followed by noun

    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_7_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
     adaptable
    0.98
     abril
    0.96
    𝚓
    0.96
    b
    0.95
     κάν
    0.93
     ແລະ
    0.93
    𝒈
    0.93
    IS
    0.91
    ちょっと
    0.91
     dizer
    0.91
    POSITIVE LOGITS
     of
    1.27
    í
    1.25
     I
    1.20
    1
    1.18
    were
    1.13
    ના
    1.02
    '
    1.02
     were
    0.95
    0.95
     was
    0.93
    Activations Density 0.001%

    No Known Activations