© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1569
    Prev
    Next
    INDEX
    Explanations

    Martin (followed by names or places)

    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_39_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
    }']
    0.36
    込め
    0.35
    结合
    0.34
    িয়েছে
    0.34
     speechSynthesis
    0.34
     علت
    0.34
    提高了
    0.34
     bese
    0.33
    '>");
    0.33
    앤
    0.33
    POSITIVE LOGITS
     Marty
    0.44
    martin
    0.43
     martin
    0.42
     mart
    0.41
     Martin
    0.39
     Scorsese
    0.38
     Prosperity
    0.38
    ík
    0.37
     нес
    0.36
    smallskip
    0.36
    Activations Density 0.021%

    No Known Activations