© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45732
    Prev
    Next
    INDEX
    Explanations

    crisis, Texas, equity

    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_3_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
     as
    0.76
    কারে
    0.67
    ва
    0.66
    一個
    0.66
    теп
    0.63
    ३
    0.62
    话
    0.61
     imparting
    0.61
    мора
    0.61
    వలం
    0.60
    POSITIVE LOGITS
    am
    1.02
    f
    0.84
    et
    0.80
    ang
    0.77
    um
    0.77
    <0x80>
    0.71
    is
    0.67
    im
    0.67
    Email
    0.66
    v
    0.65
    Activations Density 0.002%

    No Known Activations