© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53057
    Prev
    Next
    INDEX
    Explanations

    got / had + article/preposition

    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_31_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
     требуется
    0.41
     نص
    0.37
    璫
    0.37
    YN
    0.35
    |}\
    0.35
     effect
    0.35
     calendário
    0.35
     treba
    0.34
     hens
    0.34
     эффект
    0.34
    POSITIVE LOGITS
    provision
    0.43
    朋友
    0.38
    र्ती
    0.37
     taught
    0.36
    aminar
    0.36
    瑪
    0.36
    ökk
    0.35
    ccionar
    0.35
    friend
    0.35
     explosives
    0.35
    Activations Density 0.000%

    No Known Activations