© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52743
    Prev
    Next
    INDEX
    Explanations

    numerical values after labels

    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_30_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
    ometri
    0.39
     וח
    0.38
    鿁
    0.38
     удиви
    0.38
    <unused371>
    0.37
     тү
    0.36
     ન
    0.35
    leriyle
    0.35
     말을
    0.35
    牴
    0.35
    POSITIVE LOGITS
    :
    0.45
    ：
    0.44
     Eighth
    0.39
     Second
    0.39
     Seventh
    0.39
    :":
    0.39
    actions
    0.38
     guilty
    0.38
    ៖
    0.38
    :")
    0.37
    Activations Density 0.018%

    No Known Activations