© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43125
    Prev
    Next
    INDEX
    Explanations

    trade goods

    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_13_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
    am
    0.36
    eres
    0.34
    p
    0.34
    ).
    0.33
    ３
    0.32
    si
    0.31
    ede
    0.31
    al
    0.31
    gae
    0.31
    ab
    0.31
    POSITIVE LOGITS
    Yeh
    0.38
     Wenn
    0.37
    newState
    0.36
    ບໍ່
    0.36
     നേടിയ
    0.36
     نیٹ
    0.36
     इंटीग्रेशन
    0.35
    𝗡
    0.35
    ርዓ
    0.35
     criticizing
    0.35
    Activations Density 0.002%

    No Known Activations