© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53665
    Prev
    Next
    INDEX
    Explanations

    quotation marks or specific terms

    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_30_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
    छा
    0.35
    Usually
    0.34
    若
    0.34
     તૈય
    0.33
    icat
    0.33
    Đối
    0.33
    ühle
    0.33
     प्रतिनि
    0.33
    ্ঞ
    0.32
    Lors
    0.32
    POSITIVE LOGITS
     "
    0.50
     tzv
    0.45
     termed
    0.44
     tzw
    0.44
     "$
    0.43
     cosidd
    0.42
     “
    0.41
     “‘
    0.41
     ‘
    0.40
     ‘‘
    0.40
    Activations Density 0.067%

    No Known Activations