© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9283
    Prev
    Next
    INDEX
    Explanations

    technical descriptions which involve prepositions

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.89
    ]")]
    -0.84
     الحره
    -0.82
    SourceChecksum
    -0.82
     myſelf
    -0.81
     ISNI
    -0.80
     autorytatywna
    -0.78
     Houſe
    -0.78
     ModelExpression
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
     "
    0.60
     “
    0.51
     '
    0.50
     the
    0.50
     a
    0.47
     ‘
    0.47
     #
    0.42
     `
    0.41
    "
    0.40
     ’
    0.40
    Activations Density 0.738%

    No Known Activations