© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62077
    Prev
    Next
    INDEX
    Explanations

    public places

    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_2_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
    )
    1.46
    }
    1.39
     can
    1.30
    ক
    1.27
    ]
    1.23
    ad
    1.18
    ע
    1.18
    >
    1.12
    ع
    1.12
     be
    1.10
    POSITIVE LOGITS
    with
    1.06
    set
    0.99
    jaman
    0.98
    ۹
    0.97
    at
    0.96
    jší
    0.93
    ę
    0.93
    ۳
    0.91
    чный
    0.91
    ों
    0.89
    Activations Density 0.003%

    No Known Activations