© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7038
    Prev
    Next
    INDEX
    Explanations

    culmination of

    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_39_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
    krit
    0.36
    olni
    0.36
    }}+\
    0.36
     ভিন্ন
    0.36
    atini
    0.35
    leriyle
    0.35
     LOOP
    0.35
    redu
    0.33
    ❛
    0.33
     Loop
    0.33
    POSITIVE LOGITS
     lots
    1.22
     extensive
    1.16
     Considerable
    1.14
     considerable
    1.13
     countless
    1.13
    大量的
    1.10
    Lots
    1.09
    大量
    1.05
    extensive
    1.05
     প্রচুর
    1.05
    Activations Density 0.198%

    No Known Activations