© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51111
    Prev
    Next
    INDEX
    Explanations

    deal with

    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
     έτσι
    0.36
     же
    0.33
     मणि
    0.32
     हूं
    0.32
     видимо
    0.32
     conviene
    0.32
    汾
    0.32
     foncé
    0.31
    льным
    0.31
    ⇰
    0.31
    POSITIVE LOGITS
     compromises
    0.40
    Navigator
    0.39
    avoro
    0.37
     ছাড়াই
    0.37
     പിന്തുണ
    0.36
     consequences
    0.35
     spheres
    0.35
    ക്കേണ്ട
    0.35
    RAR
    0.35
    Message
    0.35
    Activations Density 0.026%

    No Known Activations