© 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. 202419
    Prev
    Next
    INDEX
    Explanations

    phase or phases

    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
    ING
    1.06
    ти
    0.97
     $
    0.88
    ка
    0.88
    ן
    0.84
     on
    0.83
    ність
    0.81
     cigars
    0.80
     an
    0.80
     vanadium
    0.80
    POSITIVE LOGITS
    ina
    1.07
    ad
    1.06
    ant
    1.01
    au
    1.00
    ين
    1.00
    és
    0.96
    r
    0.92
    es
    0.91
    ere
    0.90
    ul
    0.89
    Activations Density 0.003%

    No Known Activations