© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170016
    Prev
    Next
    INDEX
    Explanations

    tasks

    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_56_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
    দম
    0.44
     മു
    0.40
    ulah
    0.37
    ゃ
    0.37
    Brit
    0.36
    胸
    0.36
    窍
    0.36
    \}=\
    0.35
    μών
    0.35
    ፦
    0.35
    POSITIVE LOGITS
     task
    1.27
     Task
    1.15
     tasks
    1.07
    task
    1.02
    任务
    1.02
    Task
    1.01
     Tasks
    1.01
     condition
    0.98
     TASK
    0.95
     tarea
    0.94
    Activations Density 0.002%

    No Known Activations