© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145577
    Prev
    Next
    INDEX
    Explanations

    Street addresses, locations, and names

    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_0_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
    ك
    1.78
    {
    1.54
    ,
    1.30
     is
    1.27
    ка
    1.27
    ين
    1.27
    리
    1.25
    ية
    1.20
    يب
    1.20
     betekent
    1.17
    POSITIVE LOGITS
    д
    1.34
    νό
    1.33
    i
    1.30
    1
    1.30
    d
    1.27
    A
    1.16
    s
    1.12
    ui
    1.10
    y
    1.10
    al
    1.09
    Activations Density 0.000%

    No Known Activations