© 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. 35130
    Prev
    Next
    INDEX
    Explanations

    deposit insurance and depository receipts

    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
    do
    0.73
    I
    0.66
    the
    0.64
    Gün
    0.62
    alary
    0.60
    A
    0.59
    kach
    0.57
    ΗΣ
    0.57
    ด์
    0.56
     rename
    0.56
    POSITIVE LOGITS
    ча
    0.84
     deposito
    0.77
    ط
    0.70
     on
    0.69
    த்தின்
    0.67
    ми
    0.65
    на
    0.64
     depository
    0.63
     dépos
    0.63
    пу
    0.62
    Activations Density 0.000%

    No Known Activations