© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130916
    Prev
    Next
    INDEX
    Explanations

    ocelot, Lancelot, Camelot, Leilani, Iolani

    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_1_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
    b
    1.80
    c
    1.76
    v
    1.51
    d
    1.45
    p
    1.38
    r
    1.30
    an
    1.26
    m
    1.26
    ab
    1.20
    rp
    1.20
    POSITIVE LOGITS
     toiletries
    1.09
    اں
    1.06
    ↵
    1.05
    ästä
    1.03
     gaping
    1.00
     convoluted
    0.99
     teléfono
    0.99
    ıp
    0.99
     forested
    0.98
     aplicativo
    0.98
    Activations Density 0.000%

    No Known Activations