© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91849
    Prev
    Next
    INDEX
    Explanations

    media kit or entry methods

    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_11_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
     aktu
    0.12
     acusado
    0.12
     insectes
    0.11
     underwent
    0.11
     accusation
    0.11
     actualizada
    0.11
    ओ
    0.11
    ৃক
    0.11
     autoestima
    0.11
    UARY
    0.11
    POSITIVE LOGITS
    ]
    0.16
    M
    0.14
    }
    0.12
    ],
    0.12
    5
    0.11
    3
    0.11
     Macros
    0.11
    的
    0.11
    R
    0.11
    F
    0.11
    Activations Density 0.001%

    No Known Activations