© 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. 261157
    Prev
    Next
    INDEX
    Explanations

    Pragmatics, Sagmeister, Everest, Pegatron

    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
    ем
    1.15
     sclerosis
    1.07
    νο
    0.96
    ำ
    0.93
    ून
    0.92
    ीय
    0.92
    ()<<
    0.90
    ψε
    0.89
     arbor
    0.88
    ње
    0.88
    POSITIVE LOGITS
    ﺭ
    1.21
    cu
    1.13
    ח
    1.13
    can
    1.09
    c
    1.09
    all
    1.05
    ro
    1.03
    j
    1.03
    ca
    1.01
    cr
    0.98
    Activations Density 0.000%

    No Known Activations