© 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. 196662
    Prev
    Next
    INDEX
    Explanations

    formal communications

    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
     advise
    0.61
     advising
    0.48
     conseille
    0.40
     advises
    0.39
     advised
    0.39
    𝙫
    0.39
     Ec
    0.38
    Ec
    0.38
     gel
    0.38
     Gel
    0.38
    POSITIVE LOGITS
    submissions
    0.46
    ಮು
    0.43
     preferences
    0.42
     elizabeth
    0.41
    patches
    0.40
     submissions
    0.40
     cancellations
    0.39
     withdrawals
    0.38
     filings
    0.38
    preferences
    0.38
    Activations Density 0.002%

    No Known Activations