© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17056
    Prev
    Next
    INDEX
    Explanations

    example of a question

    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_34_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
     peu
    0.37
     ছু
    0.37
     Grü
    0.37
     opérés
    0.37
     कृष्णा
    0.36
     Eğ
    0.36
     Enjoy
    0.35
    𝓊
    0.35
    বন
    0.35
     বিশ্লে
    0.35
    POSITIVE LOGITS
     किस
    0.42
    __'
    0.38
     preceded
    0.37
     quel
    0.37
     กี่
    0.37
     cuantos
    0.36
     rem
    0.36
    -${
    0.35
     किसकी
    0.35
     sequent
    0.35
    Activations Density 0.155%

    No Known Activations