© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17483
    Prev
    Next
    INDEX
    Explanations

    places and landmarks

    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_34_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
    Mn
    0.42
     RetValue
    0.40
    Exists
    0.39
    biter
    0.38
    -{\
    0.37
    vegarde
    0.37
     asistir
    0.37
    hotra
    0.36
    ās
    0.35
    ={$
    0.35
    POSITIVE LOGITS
     Brewing
    0.38
     Terminal
    0.36
     Artis
    0.36
     rot
    0.36
     kic
    0.35
    rije
    0.34
    мец
    0.33
     উৎস
    0.33
     Sandwich
    0.33
     সীমা
    0.33
    Activations Density 0.025%

    No Known Activations