© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116869
    Prev
    Next
    INDEX
    Explanations

    souvenir shops

    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_27_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
     refrigerant
    0.45
     temperatura
    0.41
    糁
    0.41
     hwnd
    0.41
     beton
    0.41
    砟
    0.41
     senha
    0.40
     madrid
    0.40
    숱
    0.39
     సాం
    0.39
    POSITIVE LOGITS
     Angela
    0.40
     Morgan
    0.40
     Casey
    0.39
    uwe
    0.38
    bergs
    0.38
    point
    0.38
     Walter
    0.38
     Ezra
    0.38
    Casey
    0.38
    0.38
    Activations Density 0.001%

    No Known Activations