© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108173
    Prev
    Next
    INDEX
    Explanations

    accrue, engagement, consume

    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_1_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
    <bos>
    3.45
                         
    1.93
    ography
    1.88
     melaksanakan
    1.82
    ifica
    1.81
     britannique
    1.81
    unless
    1.80
     toString
    1.79
    luoro
    1.77
     }^{+}$
    1.76
    POSITIVE LOGITS
     时
    1.88
     годах
    1.76
     inches
    1.65
     charset
    1.65
    做
    1.53
    되었다
    1.52
    LENGTH
    1.50
     Quando
    1.50
    ..............
    1.48
     г
    1.47
    Activations Density 0.001%

    No Known Activations