© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53854
    Prev
    Next
    INDEX
    Explanations

    `?]\nAnswer`

    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_31_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
    躇
    0.44
    Regards
    0.40
    يه
    0.38
    نتی
    0.38
    rda
    0.38
    נט
    0.38
    Imagem
    0.38
    obal
    0.38
    ဦ
    0.37
    bore
    0.36
    POSITIVE LOGITS
     Depending
    0.45
     Their
    0.41
     They
    0.41
     Then
    0.40
     Any
    0.40
     Furthermore
    0.39
     ;(
    0.39
     However
    0.39
     Some
    0.39
     But
    0.38
    Activations Density 0.011%

    No Known Activations