© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167674
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    枤
    0.41
    閬
    0.40
     geologic
    0.38
     ---
    0.37
     znajdu
    0.36
     Lieblings
    0.36
    陲
    0.35
     ①
    0.34
     여기가
    0.34
     ព
    0.34
    POSITIVE LOGITS
    ished
    0.38
    ेश्वर
    0.38
    icha
    0.38
    antha
    0.37
    acchi
    0.36
    shima
    0.36
    ണ്ണം
    0.35
    ément
    0.35
     माह
    0.35
    aborasi
    0.35
    Activations Density 0.004%

    No Known Activations