© 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. 35547
    Prev
    Next
    INDEX
    Explanations

    change or action

    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
    舴
    0.44
     દિ
    0.39
    竄
    0.39
    ябре
    0.38
    Married
    0.37
    coupling
    0.37
     중국
    0.37
     velocità
    0.36
     memberikan
    0.36
    awatts
    0.36
    POSITIVE LOGITS
    sembl
    0.36
     traveled
    0.36
     المختلف
    0.36
    }})$
    0.35
     Wo
    0.34
    ânia
    0.34
    搖
    0.33
    고요
    0.33
    arke
    0.33
     schre
    0.33
    Activations Density 0.055%

    No Known Activations