© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228870
    Prev
    Next
    INDEX
    Explanations

    truth

    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_57_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
     piy
    0.44
     قرآن
    0.38
    ataka
    0.38
    ylus
    0.37
    堃
    0.37
    enial
    0.36
    沥
    0.36
    㕣
    0.36
     zuz
    0.34
     الهند
    0.34
    POSITIVE LOGITS
     truly
    0.57
    眞
    0.55
     numbers
    0.52
     Truly
    0.51
     True
    0.50
     정말
    0.50
     true
    0.49
     véritable
    0.48
     действительно
    0.48
     really
    0.48
    Activations Density 0.000%

    No Known Activations