© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35540
    Prev
    Next
    INDEX
    Explanations

    bullying and bullied

    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_11_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
    ன
    0.59
    连忙
    0.55
    它
    0.52
     रूपए
    0.49
    আ
    0.49
     Lé
    0.48
     comien
    0.48
    مركز
    0.48
    selves
    0.48
     aurez
    0.47
    POSITIVE LOGITS
    iminary
    0.53
    ical
    0.48
    icon
    0.47
    istani
    0.47
    的神
    0.47
     inquiet
    0.46
     d
    0.45
    q
    0.45
    ian
    0.44
     đối
    0.43
    Activations Density 0.026%

    No Known Activations