© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196305
    Prev
    Next
    INDEX
    Explanations

    in front of

    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
    Bond
    0.39
    icionados
    0.39
    PD
    0.38
     LA
    0.38
    ξε
    0.38
    र्द
    0.37
    预
    0.37
     Executors
    0.37
    acom
    0.37
    LA
    0.36
    POSITIVE LOGITS
     hypertro
    0.41
     How
    0.39
     비슷
    0.37
    淬
    0.37
    焯
    0.37
     suppuration
    0.37
    賄
    0.37
     কীভাবে
    0.36
     HOW
    0.36
     எப்படி
    0.36
    Activations Density 0.004%

    No Known Activations