© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44827
    Prev
    Next
    INDEX
    Explanations

    rough draft or rough sex

    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_3_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
    ر
    0.72
    September
    0.68
    b
    0.66
    m
    0.66
            
    0.62
    ل
    0.62
    h
    0.61
    buk
    0.60
    January
    0.60
    ፩
    0.59
    POSITIVE LOGITS
    ्य
    0.69
     on
    0.60
     plików
    0.59
    і
    0.59
    ती
    0.58
    ти
    0.57
     rough
    0.57
    ит
    0.57
     brasileira
    0.57
    ні
    0.56
    Activations Density 0.004%

    No Known Activations