© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167708
    Prev
    Next
    INDEX
    Explanations

    in turn influences

    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
    ડ
    0.40
    ası
    0.39
     lisää
    0.38
    増
    0.37
    pano
    0.36
    ño
    0.36
     எது
    0.36
     හැ
    0.36
     Increase
    0.36
     началом
    0.36
    POSITIVE LOGITS
    ᄐ
    0.41
     Blacks
    0.40
    बरी
    0.37
     abstr
    0.35
    нора
    0.35
    profissional
    0.35
     Augustin
    0.34
    UNION
    0.34
     tratados
    0.34
     OTHERWISE
    0.34
    Activations Density 0.002%

    No Known Activations