© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45979
    Prev
    Next
    INDEX
    Explanations

    approach, come, seek

    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_22_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
     laps
    0.28
     dosta
    0.27
     positive
    0.26
    TestAction
    0.26
    atom
    0.25
     positivo
    0.25
    8
    0.25
     oysters
    0.25
     ritmo
    0.25
     pozit
    0.25
    POSITIVE LOGITS
     seek
    0.29
    寻
    0.29
     chercher
    0.28
     présentant
    0.28
    rschein
    0.28
     предъ
    0.28
    問
    0.27
     rechercher
    0.27
     για
    0.27
     seeks
    0.27
    Activations Density 0.028%

    No Known Activations