Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261559
    Prev
    Next
    INDEX
    Explanations

    height difference, Monero (XMR),LAGUER

    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
    v
    1.67
    .
    1.63
    p
    1.51
    '
    1.50
     that
    1.49
    2
    1.45
    that
    1.39
    ست
    1.38
    of
    1.34
    se
    1.30
    POSITIVE LOGITS
    त
    1.13
     மட்டு
    0.99
     взя
    0.96
     rupam
    0.92
     Kyrgios
    0.91
    ં
    0.91
    ನ
    0.91
    autoarima
    0.90
     frosty
    0.90
     sociable
    0.88
    Activations Density 0.000%

    No Known Activations