© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165320
    Prev
    Next
    INDEX
    Explanations

    sheesh, bless, blursed

    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_13_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
     wobec
    0.54
     advogado
    0.54
    ţ
    0.51
    ът
    0.51
     laminated
    0.49
     кандай
    0.49
     Цена
    0.49
     wię
    0.48
    adona
    0.47
    ột
    0.47
    POSITIVE LOGITS
    Battle
    0.50
     correlates
    0.50
     Heels
    0.50
    SE
    0.47
     Herzen
    0.47
    Technologies
    0.46
    新技术
    0.46
    合物
    0.46
    J
    0.45
    Glasses
    0.44
    Activations Density 0.000%

    No Known Activations