© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198173
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    ദ്യം
    0.39
    സിൽ
    0.39
     belül
    0.39
    }+...
    0.38
    लिसा
    0.38
     postcss
    0.37
     naturel
    0.37
    Pessoal
    0.37
    getStartState
    0.37
    Lucida
    0.36
    POSITIVE LOGITS
     endings
    0.37
    oju
    0.36
     flame
    0.36
    equival
    0.36
     ceramic
    0.35
    瞥
    0.35
    otal
    0.34
     cry
    0.34
     crying
    0.34
     заканчи
    0.34
    Activations Density 0.000%

    No Known Activations