© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87852
    Prev
    Next
    INDEX
    Explanations

    don't care / doesn't matter

    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_23_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
     Your
    0.38
    Your
    0.37
     "\
    0.37
     "@
    0.37
    Abs
    0.36
    Charged
    0.36
     S
    0.35
    $.
    0.35
     SPRING
    0.34
     الس
    0.34
    POSITIVE LOGITS
     ideally
    0.44
     famí
    0.44
    quir
    0.42
     eût
    0.42
    बाज
    0.41
     Ideally
    0.41
    berts
    0.41
     qualquer
    0.41
     aberr
    0.40
     invertebr
    0.40
    Activations Density 0.002%

    No Known Activations