© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224839
    Prev
    Next
    INDEX
    Explanations

    common prepositions and determiners

    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_10_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
    作った
    0.57
    <0x95>
    0.55
     McCormack
    0.55
     francês
    0.53
     शही
    0.52
    こうした
    0.52
    <0x93>
    0.51
    フランス
    0.51
    ೖ
    0.51
     français
    0.50
    POSITIVE LOGITS
    I
    0.56
    as
    0.49
     I
    0.48
     braids
    0.47
    ty
    0.47
      
    0.45
    od
    0.44
     contest
    0.44
     چشم
    0.43
    öt
    0.42
    Activations Density 0.000%

    No Known Activations