© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54343
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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_31_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
    jati
    0.40
    ḍ
    0.36
    hat
    0.35
     coexist
    0.35
     strike
    0.35
    HAT
    0.35
    Plane
    0.34
     deprive
    0.34
     Somers
    0.34
    ^[
    0.34
    POSITIVE LOGITS
    如果是
    0.45
     kalau
    0.39
    ถ้า
    0.39
     אם
    0.39
    фициа
    0.39
     autoridad
    0.38
     कड़ी
    0.38
     Tân
    0.37
     fruta
    0.37
     अगर
    0.37
    Activations Density 0.024%

    No Known Activations