© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196048
    Prev
    Next
    INDEX
    Explanations

    purification and cleansing

    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_27_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
    빽
    0.43
    𒈹
    0.42
    偶然
    0.41
    ukone
    0.40
     poteva
    0.40
     المستقيم
    0.39
    Consistent
    0.39
    encoded
    0.39
    ͒
    0.39
    ᵔ
    0.38
    POSITIVE LOGITS
     walk
    0.44
     walkthrough
    0.44
     disaster
    0.39
     Sale
    0.39
     social
    0.38
    西方
    0.37
     PC
    0.36
     cap
    0.36
     dodge
    0.36
     Walk
    0.35
    Activations Density 0.002%

    No Known Activations