© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237554
    Prev
    Next
    INDEX
    Explanations

    google maps links

    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
     Pfarr
    0.19
     intervent
    0.19
    只限平日
    0.18
    RIBUT
    0.18
     Knud
    0.17
     seyd
    0.17
     نفس
    0.17
    렀
    0.17
     רק
    0.17
     قوت
    0.17
    POSITIVE LOGITS
    imeters
    0.21
     Facilit
    0.20
     Amazing
    0.19
     Network
    0.18
    lead
    0.18
     Mesh
    0.17
    participants
    0.17
     facilitators
    0.17
    wall
    0.17
     sorties
    0.17
    Activations Density 0.001%

    No Known Activations