© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89490
    Prev
    Next
    INDEX
    Explanations

    double-sided, double-acting, bidirectional

    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_23_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
     mutter
    0.38
    global
    0.36
    fun
    0.35
    }}=-\
    0.35
    ,]$
    0.35
    /**
    0.35
     fluke
    0.34
    ]//
    0.34
     penalty
    0.34
    </footer>
    0.33
    POSITIVE LOGITS
    襲
    0.45
     Pubmed
    0.41
     መጠ
    0.41
     मिताली
    0.40
     mogelijkheden
    0.40
     সকাল
    0.40
    郤
    0.40
     možnost
    0.40
     সম্ভাবনা
    0.39
     ஏனெ
    0.39
    Activations Density 0.001%

    No Known Activations