© 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. 39544
    Prev
    Next
    INDEX
    Explanations

    Foreign Direct Investment

    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
    </h3>
    0.71
    ี
    0.68
     turno
    0.64
    ط
    0.64
    ס
    0.64
     terminer
    0.64
    ası
    0.63
     nuovo
    0.63
     ingreso
    0.63
     morto
    0.63
    POSITIVE LOGITS
    a
    1.01
    ه
    0.92
    S
    0.85
    I
    0.83
    O
    0.82
    o
    0.82
    ab
    0.80
    in
    0.79
    em
    0.75
    ar
    0.74
    Activations Density 0.002%

    No Known Activations