© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141620
    Prev
    Next
    INDEX
    Explanations

    barrier protection and condoms

    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_12_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
    hidrat
    0.46
    iscal
    0.42
    izar
    0.41
     rozwo
    0.41
     قلي
    0.40
    self
    0.40
    azionale
    0.40
    N
    0.40
    iau
    0.39
    Temper
    0.39
    POSITIVE LOGITS
    टन
    0.47
     condoms
    0.46
     SEXUAL
    0.46
     сексуа
    0.44
     VIH
    0.43
    ↵
    0.40
     Bishops
    0.39
     Except
    0.38
     FEES
    0.38
     HIV
    0.38
    Activations Density 0.002%

    No Known Activations