© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130643
    Prev
    Next
    INDEX
    Explanations

    buy or sell

    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_25_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
    Waterfall
    0.41
     reflectors
    0.41
    Yours
    0.40
    ThemeOverlay
    0.39
    Roxy
    0.38
    ǝ
    0.38
     princesses
    0.38
     girlfriends
    0.37
     hostels
    0.37
    <unused24>
    0.36
    POSITIVE LOGITS
     😂
    0.40
     Mathemat
    0.40
     असामान्य
    0.38
     profondément
    0.37
    <tbody>
    0.37
    izienz
    0.37
     или
    0.36
    時
    0.36
     अन
    0.36
    ipsych
    0.36
    Activations Density 0.001%

    No Known Activations