© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225584
    Prev
    Next
    INDEX
    Explanations

    persecution / persecución

    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_10_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
    t
    0.17
     entitle
    0.16
     afford
    0.16
     allowance
    0.16
    lcl
    0.16
     entail
    0.15
     drawRight
    0.15
     extérieur
    0.15
    т
    0.15
    :")
    0.15
    POSITIVE LOGITS
    ia
    0.18
    ма
    0.17
    getStringExtra
    0.17
    on
    0.17
    stream
    0.17
    ча
    0.17
    ie
    0.16
    eta
    0.16
     Kullan
    0.16
    star
    0.16
    Activations Density 0.008%

    No Known Activations