© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4506
    Prev
    Next
    INDEX
    Explanations

    Delaware

    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_38_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
    splunk
    0.43
    jonal
    0.41
     cục
    0.40
    ｆ
    0.40
    辍
    0.40
    潦
    0.39
    道具
    0.39
    匱
    0.39
    滇
    0.38
    feel
    0.38
    POSITIVE LOGITS
     Delaware
    0.68
     bay
    0.46
     bays
    0.46
     Bays
    0.44
     Bay
    0.43
     BAY
    0.43
     motorcycle
    0.42
     Wilmington
    0.42
    uvo
    0.41
     bypass
    0.40
    Activations Density 0.002%

    No Known Activations