© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78549
    Prev
    Next
    INDEX
    Explanations

    replaced by

    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_31_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
    ᑎ
    0.43
     பதிலாக
    0.42
    แรก
    0.39
    倍
    0.39
    代替
    0.38
     পছ
    0.37
    ᒡ
    0.36
    ಮಾನ
    0.36
    *)
    0.36
     plein
    0.36
    POSITIVE LOGITS
    allocation
    0.42
     grappling
    0.42
     allocation
    0.41
     allocations
    0.41
     allocating
    0.38
     Tertiary
    0.38
     Allocation
    0.37
     consequence
    0.36
    这是一
    0.36
     difficult
    0.36
    Activations Density 0.006%

    No Known Activations