© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20337
    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_56_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
     Frequently
    0.41
     val
    0.40
    iovascular
    0.39
    Frequently
    0.38
     frequently
    0.37
    ավ
    0.36
    From
    0.36
    </h2>
    0.35
    val
    0.35
    UU
    0.35
    POSITIVE LOGITS
     alignment
    0.94
     aligned
    0.89
     alignments
    0.86
     aligning
    0.86
    alignment
    0.84
     Alignment
    0.84
    Alignment
    0.80
     align
    0.79
     Align
    0.77
    Align
    0.74
    Activations Density 0.000%

    No Known Activations