© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261236
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    ized
    1.28
     of
    1.20
    ).
    1.20
    ’
    1.15
    its
    1.05
    ]
    1.02
    ished
    1.01
    izer
    0.98
    ся
    0.97
    ize
    0.96
    POSITIVE LOGITS
    ir
    1.43
    ا
    1.41
    ي
    1.31
    做
    1.30
    아
    1.20
    وأ
    1.18
    ா
    1.16
    اك
    1.14
    ك
    1.14
    数据
    1.11
    Activations Density 0.016%

    No Known Activations