© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102264
    Prev
    Next
    INDEX
    Explanations

    bomb disposal, bombastic, bomb-making

    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_14_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
    y
    0.17
     ST
    0.15
    KE
    0.15
    ind
    0.14
    ”)
    0.14
    AST
    0.14
    ’
    0.13
     EE
    0.13
    }
    0.13
     CMA
    0.13
    POSITIVE LOGITS
     ativar
    0.17
    aisseur
    0.16
     세포
    0.16
    面膜
    0.16
    щает
    0.16
     পাকিস্ত
    0.16
     வால்பேப்பர்
    0.16
     actief
    0.16
     பல்கலைக்கழக
    0.16
    𝚍
    0.15
    Activations Density 0.004%

    No Known Activations