© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16558
    Prev
    Next
    INDEX
    Explanations

    web links and code references

    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_34_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
    ალაქ
    0.38
    kannten
    0.38
    一枚
    0.36
    ዲስ
    0.36
    yuk
    0.36
    julia
    0.36
    觎
    0.36
    forward
    0.35
    mitt
    0.35
    ambo
    0.35
    POSITIVE LOGITS
    Equity
    0.39
    拆
    0.39
     Equity
    0.38
     equity
    0.36
    ۆ
    0.36
     modificar
    0.35
     snacks
    0.34
     rehabilitated
    0.34
    воз
    0.34
     Ł
    0.34
    Activations Density 0.007%

    No Known Activations