© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44745
    Prev
    Next
    INDEX
    Explanations

    rock, soil, and geological type

    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
     kleine
    0.37
    edo
    0.34
    年以上
    0.33
    মাকে
    0.33
    czka
    0.32
    enswert
    0.32
    }}{\
    0.32
     bijna
    0.32
    <0x16>
    0.31
    sta
    0.31
    POSITIVE LOGITS
     delving
    0.38
     failures
    0.37
     aryl
    0.35
     Ayrıca
    0.32
     intolerable
    0.32
     catastrophic
    0.32
     tyranny
    0.31
     P
    0.30
     unable
    0.30
    Мо
    0.30
    Activations Density 0.026%

    No Known Activations