© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169451
    Prev
    Next
    INDEX
    Explanations

    learning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    起
    0.64
    起的
    0.53
    起了
    0.51
     起
    0.45
     closely
    0.41
    ː
    0.41
    )【
    0.38
    :‏
    0.38
    为何
    0.37
    ,​
    0.37
    POSITIVE LOGITS
     |
    0.46
    leen
    0.39
    ounds
    0.37
    ൾ
    0.37
     scram
    0.37
    learn
    0.36
    ---|
    0.35
    learning
    0.35
    tral
    0.35
    cort
    0.34
    Activations Density 0.000%

    No Known Activations