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. 261884
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    c
    1.19
    z
    1.13
    ك
    1.11
    ان
    1.09
    ка
    1.08
    )
    1.06
    b
    1.05
    د
    1.02
    ch
    0.98
    ela
    0.98
    POSITIVE LOGITS
    as
    1.27
    1
    1.24
    يد
    1.20
     of
    1.13
    0
    1.10
    ת
    1.09
    ೋ
    1.09
    তা
    1.06
    เป็น
    1.06
    2
    1.04
    Activations Density 0.000%

    No Known Activations