© 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. 131370
    Prev
    Next
    INDEX
    Explanations

    SQuAD dataset

    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
    У
    1.43
    С
    1.41
    К
    1.39
    А
    1.27
    の
    1.27
    もの
    1.18
    Ο
    1.17
    Ре
    1.16
    Т
    1.13
    AL
    1.12
    POSITIVE LOGITS
    ong
    0.98
    enen
    0.90
    j
    0.84
    ení
    0.83
    el
    0.83
    ě
    0.82
    ill
    0.81
     QSOs
    0.81
    ieht
    0.79
    igned
    0.79
    Activations Density 0.000%

    No Known Activations