© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109630
    Prev
    Next
    INDEX
    Explanations

    Hiragana

    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_2_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
    is
    1.12
    y
    1.06
    ut
    1.00
     compone
    0.91
    g
    0.90
    ir
    0.90
     stemmed
    0.88
    il
    0.86
    де
    0.86
    தான்
    0.84
    POSITIVE LOGITS
    た
    1.30
    1
    1.27
    া
    1.24
    О
    1.24
    اً
    1.23
    ),
    1.09
    Y
    1.05
     \
    1.02
     و
    1.02
    CE
    1.02
    Activations Density 0.000%

    No Known Activations