© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91051
    Prev
    Next
    INDEX
    Explanations

    parts of a conversation or plan

    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_11_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
     bare
    0.52
    它們
    0.51
     legge
    0.50
    :
    0.48
    SCH
    0.46
     factoring
    0.46
     forklift
    0.46
    Social
    0.46
    RL
    0.46
     แอป
    0.45
    POSITIVE LOGITS
    ъ
    0.55
    ین
    0.54
    ęt
    0.51
    ёт
    0.48
    은
    0.46
    на
    0.46
    или
    0.46
    ồ
    0.46
    ኑ
    0.46
    می
    0.45
    Activations Density 0.000%

    No Known Activations