© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201018
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    )
    1.34
    _
    1.18
    9
    1.14
     by
    1.10
    {
    1.10
    ]
    1.09
    8
    1.02
    }
    0.99
    ING
    0.91
    5
    0.91
    POSITIVE LOGITS
    ки
    1.19
    ви
    1.16
    то
    1.10
    тина
    1.05
    enciais
    1.04
    ύ
    1.03
    да
    1.02
     সময়
    1.01
    сет
    0.99
    ът
    0.98
    Activations Density 0.000%

    No Known Activations