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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127030
    Prev
    Next
    INDEX
    Explanations

    **black and white concepts**

    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_37_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
     mermaid
    0.64
     tails
    0.64
    mermaid
    0.61
     tail
    0.59
     Mermaid
    0.58
    🧜
    0.58
    tails
    0.56
     Tails
    0.54
    Tail
    0.52
     monof
    0.50
    POSITIVE LOGITS
     white
    0.52
     Black
    0.48
     black
    0.47
     White
    0.47
    White
    0.46
    white
    0.46
    白
    0.45
    WHITE
    0.44
     teknik
    0.43
     ब्लैक
    0.43
    Activations Density 0.005%

    No Known Activations