© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14947
    Prev
    Next
    INDEX
    Explanations

    section titles/paper keywords

    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_34_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
     Ciencias
    0.36
     scienze
    0.34
    笆
    0.34
     aras
    0.33
     ciencias
    0.32
    াজের
    0.31
    ReturnValue
    0.30
     العلوم
    0.30
    aseña
    0.30
     വൈദ്യ
    0.30
    POSITIVE LOGITS
    独
    0.38
    そう
    0.34
     Comparing
    0.34
    灵活
    0.33
     применения
    0.32
    Comparing
    0.32
     독
    0.31
    PrivateRoute
    0.31
    nění
    0.30
     Introducing
    0.30
    Activations Density 0.011%

    No Known Activations