© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116100
    Prev
    Next
    INDEX
    Explanations

    starts relatively quiet or straightforward

    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_27_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
    ontaneous
    0.35
     terminating
    0.34
     পেরিয়ে
    0.34
     oversight
    0.34
    魄
    0.34
    ranu
    0.33
    ფილი
    0.33
     terminated
    0.33
     काढ
    0.33
    结束
    0.33
    POSITIVE LOGITS
     jim
    0.42
    packer
    0.42
    렵
    0.41
    ᵁ
    0.40
    چار
    0.39
    apte
    0.39
    нім
    0.39
     Hopper
    0.39
    Kl
    0.38
     impatience
    0.38
    Activations Density 0.004%

    No Known Activations