© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65004
    Prev
    Next
    INDEX
    Explanations

    bamboo

    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_46_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
     округу
    0.38
     prayed
    0.38
     joke
    0.37
     agres
    0.36
     МО
    0.36
    மார
    0.36
    ὠ
    0.36
     moan
    0.35
    ableness
    0.35
    黄色
    0.35
    POSITIVE LOGITS
    Bamboo
    1.36
     Bamboo
    1.34
     bamb
    1.33
    竹
    1.27
     bamboo
    1.26
     Bamb
    1.24
     竹
    1.11
     BAM
    1.03
    Bam
    0.99
     Bam
    0.95
    Activations Density 0.000%

    No Known Activations