© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11317
    Prev
    Next
    INDEX
    Explanations

    DOE Options, Essence Reaver

    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_13_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
    };
    0.21
    es
    0.20
    }
    0.20
    ene
    0.18
    ы
    0.18
    },
    0.18
    }}
    0.18
    eno
    0.17
    hen
    0.17
    ّم
    0.17
    POSITIVE LOGITS
    𝙎
    0.22
     dragonfly
    0.20
     ਪ
    0.19
     嗯
    0.19
    导航
    0.19
     stratigraphic
    0.19
    ಗಳು
    0.19
    蝴
    0.19
     জন্য
    0.18
     doorstep
    0.18
    Activations Density 0.008%

    No Known Activations