© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60463
    Prev
    Next
    INDEX
    Explanations

    predictive power

    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_11_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
     were
    0.51
    憂
    0.51
    ň
    0.51
    kan
    0.50
    忧
    0.47
    Kom
    0.46
     कड़ी
    0.46
     Were
    0.46
     उपलब्धि
    0.46
    फल
    0.45
    POSITIVE LOGITS
     e
    0.49
     confr
    0.45
    attiyam
    0.45
    imidazole
    0.43
     direita
    0.43
    си
    0.43
    нию
    0.41
    anud
    0.41
     imidazole
    0.41
    igrade
    0.41
    Activations Density 0.008%

    No Known Activations