© 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
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 212670
    Prev
    Next
    INDEX
    Explanations

    contraptions

    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_5_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
    al
    0.96
    いますが
    0.82
     Реа
    0.76
     كما
    0.76
    Parameteri
    0.75
    SDLCheck
    0.75
    ありますが
    0.73
    +}$
    0.71
     Пока
    0.71
    alisation
    0.71
    POSITIVE LOGITS
     to
    1.86
     with
    1.18
     is
    1.16
     It
    1.14
    \
    1.09
     it
    0.99
     you
    0.96
     or
    0.93
     uang
    0.89
    য়
    0.89
    Activations Density 0.000%

    No Known Activations