© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197157
    Prev
    Next
    INDEX
    Explanations

    still active or ongoing

    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_27_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
     Stry
    0.35
    ﮑ
    0.34
    ಹ್
    0.34
    VICIO
    0.33
    గ్
    0.33
    carte
    0.33
     நொ
    0.32
     saddhim
    0.32
    妮
    0.32
     humanidad
    0.32
    POSITIVE LOGITS
     av
    0.40
     Fellows
    0.37
     abo
    0.36
     scenarios
    0.35
     đc
    0.34
     được
    0.33
     utils
    0.33
     TV
    0.32
     ay
    0.32
     begitu
    0.32
    Activations Density 0.002%

    No Known Activations