© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 204967
    Prev
    Next
    INDEX
    Explanations

    CTC, CTG, or NDR

    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_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
     is
    1.04
     diese
    0.92
     warto
    0.88
    ه
    0.88
     dieses
    0.86
    ко
    0.84
     lumière
    0.81
    ань
    0.80
     그는
    0.79
     mechanistic
    0.79
    POSITIVE LOGITS
    of
    1.09
    ).
    1.09
    2
    1.04
    )。
    0.94
    ده
    0.92
    ,
    0.92
    ด์
    0.89
    Kin
    0.86
    كي
    0.86
    ),
    0.84
    Activations Density 0.000%

    No Known Activations