© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204685
    Prev
    Next
    INDEX
    Explanations

    responsibility

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ((\
    0.50
     }(\
    0.47
     arbeit
    0.47
    我們要
    0.44
    㐹
    0.43
     arbeiten
    0.41
     статисти
    0.41
     arbeitet
    0.40
     CDF
    0.40
    }=(\
    0.39
    POSITIVE LOGITS
    Respons
    0.46
    resp
    0.43
    sync
    0.42
     مسؤول
    0.42
    clouds
    0.41
     sync
    0.40
    CONT
    0.39
     responsabilidad
    0.39
    cont
    0.39
    prof
    0.38
    Activations Density 0.010%

    No Known Activations