© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10027
    Prev
    Next
    INDEX
    Explanations

    am and iam

    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_40_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
     Everyone
    0.39
    皐
    0.38
    TRO
    0.36
    クサ
    0.35
     Unlike
    0.34
    ylmethylsulfanyl
    0.34
    月から
    0.33
    汋
    0.33
     جشنواره
    0.33
    thorne
    0.32
    POSITIVE LOGITS
    sterdam
    0.61
    algam
    0.46
    irez
    0.43
    Am
    0.42
    تحان
    0.41
     amd
    0.40
    iam
    0.39
     timeCounter
    0.39
     iam
    0.39
     amide
    0.38
    Activations Density 0.143%

    No Known Activations