© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177358
    Prev
    Next
    INDEX
    Explanations

    conjunctions or specific words

    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_24_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
    }
    0.43
     Britain
    0.42
     ఒక్క
    0.42
     }
    0.41
     :)
    0.41
     Presley
    0.39
     culprits
    0.39
    }\
    0.38
    }.
    0.38
     Tiere
    0.37
    POSITIVE LOGITS
    зили
    0.43
    수에
    0.41
     dynamique
    0.41
    금을
    0.39
     근
    0.38
     zároveň
    0.38
     paradigma
    0.38
    摹
    0.38
    סים
    0.37
    훌
    0.37
    Activations Density 0.036%

    No Known Activations