© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257667
    Prev
    Next
    INDEX
    Explanations

    dual degree or nationality

    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_22_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
    𝟭
    0.43
    ropol
    0.42
    𝚆
    0.41
    𝙧
    0.39
    𝙱
    0.39
    햇
    0.39
     netted
    0.39
    कारक
    0.39
    𝚎
    0.39
    etermin
    0.39
    POSITIVE LOGITS
     litmus
    0.44
    ________________
    0.39
     rig
    0.38
     createTask
    0.37
    quests
    0.37
     musí
    0.37
    πος
    0.37
     implementations
    0.37
    Rig
    0.37
     lindos
    0.36
    Activations Density 0.000%

    No Known Activations