© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225887
    Prev
    Next
    INDEX
    Explanations

    target

    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_10_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
    та
    0.44
    )
    0.43
    ).
    0.42
    ва
    0.41
    )."
    0.40
    </h1>
    0.39
    ることができる
    0.39
    ώσεις
    0.38
    的神
    0.38
    ></
    0.37
    POSITIVE LOGITS
    Target
    0.72
     target
    0.70
     targets
    0.70
     Target
    0.70
    target
    0.64
    Targets
    0.63
     TARGET
    0.61
     cible
    0.61
     Targets
    0.61
     alvo
    0.60
    Activations Density 0.020%

    No Known Activations