© 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-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4068
    Prev
    Next
    INDEX
    Explanations

    references to transcription processes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.56
     Shops
    -0.53
    flink
    -0.52
    anga
    -0.51
     shops
    -0.51
    Reserved
    -0.51
    LatLng
    -0.51
    DateField
    -0.51
     Tre
    -0.50
     Kenn
    -0.49
    POSITIVE LOGITS
     transcription
    2.78
     Transcription
    2.45
    transcription
    2.25
    Transcription
    2.08
     transcriptional
    1.76
     transcribed
    1.51
    SCRIPTION
    0.99
    Transcript
    0.90
     transcrip
    0.90
    Transkript
    0.89
    Activations Density 0.010%

    No Known Activations