© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150787
    Prev
    Next
    INDEX
    Explanations

    turned, pressed, dropped

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    Remain
    0.48
    䀦
    0.43
    Initially
    0.41
     pozosta
    0.41
     inicialmente
    0.39
     Remain
    0.38
     оста
    0.37
    ENDMENT
    0.37
    ᱣ
    0.37
     deği
    0.37
    POSITIVE LOGITS
     turned
    0.65
     pressed
    0.64
     drop
    0.58
     pushed
    0.57
     emphasise
    0.54
    pressed
    0.51
     colour
    0.50
     colours
    0.49
     Pressed
    0.49
    drop
    0.48
    Activations Density 0.000%

    No Known Activations