© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214539
    Prev
    Next
    INDEX
    Explanations

    costa, cost, coastal

    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_5_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
    1.92
    q
    1.38
    ק
    1.32
     as
    1.27
    ()
    1.27
    ANG
    1.26
    DA
    1.21
    י
    1.16
     and
    1.16
    una
    1.13
    POSITIVE LOGITS
    al
    1.20
    ról
    1.14
     convoluted
    1.09
    ीडी
    1.07
    aloko
    1.05
     tecnológicas
    1.05
    níka
    1.03
    lardan
    1.02
     descarga
    1.02
    alama
    1.02
    Activations Density 0.000%

    No Known Activations