© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131356
    Prev
    Next
    INDEX
    Explanations

    any that might

    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_6_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
    w
    1.36
    b
    1.29
    v
    1.27
    j
    1.23
    f
    1.22
    x
    1.12
    at
    1.10
    m
    1.09
    k
    1.08
    ay
    1.07
    POSITIVE LOGITS
     on
    1.02
     čo
    0.92
    ദ്ധതി
    0.88
     interne
    0.85
     öffentliche
    0.85
     कु
    0.83
     Dialog
    0.83
     البرنامج
    0.82
     malicious
    0.82
     mögliche
    0.80
    Activations Density 0.006%

    No Known Activations