© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236379
    Prev
    Next
    INDEX
    Explanations

    decentralized social media

    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_46_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
    utely
    0.38
    бы
    0.38
    édon
    0.35
     disequ
    0.35
    ოლოდ
    0.34
     rõ
    0.34
     proximal
    0.34
    료
    0.34
    ẩn
    0.34
    决
    0.34
    POSITIVE LOGITS
    psr
    0.48
    Timeline
    0.43
    policies
    0.41
     Greta
    0.41
    பாட
    0.41
     Went
    0.40
    Test
    0.40
     gehen
    0.40
    verages
    0.40
     Timeline
    0.40
    Activations Density 0.001%

    No Known Activations