© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206194
    Prev
    Next
    INDEX
    Explanations

    Bible version citations

    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_20_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
    0
    0.45
    IN
    0.44
    UT
    0.44
    ch
    0.43
     complexes
    0.43
     units
    0.43
    orifice
    0.43
    3
    0.41
    zzle
    0.40
    s
    0.40
    POSITIVE LOGITS
    ையடுத்து
    0.43
    крови
    0.43
    чатку
    0.43
    Penumpang
    0.43
     سريع
    0.42
    Luong
    0.41
     incluem
    0.41
     chargingStation
    0.41
    בּ
    0.40
     يعني
    0.40
    Activations Density 0.000%

    No Known Activations