© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203494
    Prev
    Next
    INDEX
    Explanations

    home country language

    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_25_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
     Venezia
    0.29
     VS
    0.29
    节能
    0.28
     Vedi
    0.27
     Virginia
    0.26
     Gibraltar
    0.26
     Dusk
    0.26
    3
    0.26
     Venetian
    0.26
    auh
    0.26
    POSITIVE LOGITS
    Collide
    0.27
    collide
    0.27
     twist
    0.25
     आविष्कार
    0.25
     paral
    0.24
    Answers
    0.24
    萝卜
    0.24
     പിന്ന
    0.23
    ordinate
    0.23
    manufacturing
    0.23
    Activations Density 0.002%

    No Known Activations