© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67018
    Prev
    Next
    INDEX
    Explanations

    terminal value

    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_41_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
    WP
    0.42
    న్న
    0.40
    cloak
    0.40
    ইডি
    0.39
    XI
    0.39
    織
    0.38
    喬
    0.38
     અર
    0.37
     DOP
    0.36
     Warp
    0.36
    POSITIVE LOGITS
     terminal
    3.05
    Terminal
    2.78
    terminal
    2.75
     Terminal
    2.73
     टर्मिनल
    2.33
    终端
    2.30
     terminals
    2.28
     термина
    1.99
     TERMIN
    1.84
    TERMIN
    1.70
    Activations Density 0.002%

    No Known Activations