© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46928
    Prev
    Next
    INDEX
    Explanations

    The Problem of Evil

    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_3_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
    0.75
    ה
    0.66
    המ
    0.64
    ان
    0.63
    しの
    0.61
    う
    0.59
    מ
    0.59
    同じ
    0.58
    meg
    0.57
    ע
    0.57
    POSITIVE LOGITS
    к
    0.71
    ла
    0.69
    за
    0.66
     എന്നാല്‍
    0.64
     },
    0.62
    ியை
    0.61
     пользователи
    0.59
    га
    0.59
     бону
    0.59
     advertise
    0.59
    Activations Density 0.000%

    No Known Activations