© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175592
    Prev
    Next
    INDEX
    Explanations

    more / what more

    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_20_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
    м
    0.41
     K
    0.39
     разнови
    0.38
     categorie
    0.38
    たとえば
    0.38
     bollywood
    0.38
     successively
    0.37
     ソ
    0.37
     M
    0.37
     categories
    0.37
    POSITIVE LOGITS
    pherds
    0.44
    étaient
    0.43
     compacted
    0.41
    емый
    0.40
    maskedTextBox
    0.40
    িনবার্গ
    0.39
    掌控
    0.38
    arendon
    0.37
    InMemory
    0.37
     गोपनीय
    0.37
    Activations Density 0.000%

    No Known Activations