© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197047
    Prev
    Next
    INDEX
    Explanations

    say "i" words

    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_50_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
     Ants
    0.68
     Ant
    0.63
    Ant
    0.63
     antenna
    0.63
     antennas
    0.62
     অ্যান্ট
    0.62
    蚂
    0.62
    螞
    0.61
     antennae
    0.59
     Antenna
    0.58
    POSITIVE LOGITS
     Bl
    0.52
     ब्ल
    0.48
     블
    0.47
    Bl
    0.44
     bl
    0.43
     RUS
    0.42
     Bluff
    0.41
     giusta
    0.40
     BL
    0.39
    عرض
    0.37
    Activations Density 0.000%

    No Known Activations