© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196153
    Prev
    Next
    INDEX
    Explanations

    this is not exhaustive

    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_26_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
    帶來
    0.24
     стать
    0.24
    带来
    0.24
    灵
    0.23
     Rússia
    0.22
    do
    0.22
    ण्या
    0.22
    崁
    0.22
    氟
    0.22
    让
    0.22
    POSITIVE LOGITS
     newbie
    0.24
     percep
    0.23
    ，”
    0.22
     Idiot
    0.22
     Ordinance
    0.22
    chloric
    0.21
     Tablet
    0.21
     Initialize
    0.20
     isotropic
    0.20
     Acceleration
    0.20
    Activations Density 0.028%

    No Known Activations