© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195892
    Prev
    Next
    INDEX
    Explanations

    lines

    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
     honest
    0.48
    ceived
    0.39
     Federation
    0.39
    薢
    0.39
    roses
    0.38
    quired
    0.38
     awhile
    0.37
    終わり
    0.37
     Honest
    0.37
    поло
    0.37
    POSITIVE LOGITS
     культур
    0.41
    Invocation
    0.40
    𝕀
    0.40
    ніципа
    0.38
    НК
    0.38
    𝐍
    0.38
    Landing
    0.37
     Merkel
    0.37
    Municipal
    0.37
    Ava
    0.36
    Activations Density 0.016%

    No Known Activations