© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7345
    Prev
    Next
    INDEX
    Explanations

    abdomen, anal sex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    𝚍
    2.13
    ты
    2.01
    𝚝
    1.94
    된
    1.89
    ून
    1.88
     excuse
    1.88
    at
    1.86
    ص
    1.83
    度が
    1.79
    )}{\
    1.76
    POSITIVE LOGITS
    𝘴
    2.52
    𝘤
    2.41
    𝘣
    2.13
    𝘨
    2.12
     стороне
    2.11
    鐩
    2.05
    𝘱
    2.02
    𝘸
    1.99
     forth
    1.99
    𝘪
    1.94
    Activations Density 0.062%

    No Known Activations