© 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. 206031
    Prev
    Next
    INDEX
    Explanations

    long-haul routes

    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
     Infants
    0.47
     tmp
    0.45
     tamar
    0.43
     PROGRAMS
    0.42
     Texts
    0.42
     scattered
    0.41
    Heights
    0.41
    ₜ
    0.41
     numeros
    0.41
     Symbols
    0.41
    POSITIVE LOGITS
    障
    0.43
    pland
    0.40
    сом
    0.40
    slan
    0.40
    совой
    0.39
    త్తి
    0.39
    товой
    0.39
    oglou
    0.39
     серии
    0.38
    hes
    0.38
    Activations Density 0.002%

    No Known Activations