© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133674
    Prev
    Next
    INDEX
    Explanations

    taxpayer dollars identification

    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_6_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
    ння
    1.04
     offrant
    0.92
     escrit
    0.84
    йна
    0.82
     indiquant
    0.82
    يو
    0.81
    νη
    0.80
    ى
    0.79
     on
    0.78
    готов
    0.77
    POSITIVE LOGITS
    da
    1.36
    er
    1.30
     a
    1.23
    d
    1.21
    ant
    1.20
    ton
    1.20
    der
    1.16
    ts
    1.14
    ties
    0.96
    dt
    0.96
    Activations Density 0.000%

    No Known Activations