© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51506
    Prev
    Next
    INDEX
    Explanations

    purpose of god

    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_30_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
     chrét
    0.44
    ραν
    0.43
    精华
    0.43
    膻
    0.41
     cristianos
    0.41
    ဴ
    0.40
     TreeNode
    0.40
    关节
    0.39
    驳
    0.39
    失败
    0.39
    POSITIVE LOGITS
     ষ
    0.37
    well
    0.36
     jacks
    0.35
     hands
    0.35
    isk
    0.35
     *}$
    0.35
     ইতো
    0.35
     slams
    0.34
     archaeologist
    0.34
     Well
    0.34
    Activations Density 0.000%

    No Known Activations