© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11351
    Prev
    Next
    INDEX
    Explanations

    text regarding encouragement, potential, and how things will be

    oai_token-act-pair · gemini-2.0-flash

    and or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     helping
    -0.81
    Helping
    -0.74
     Helping
    -0.73
    Allows
    -0.69
     helps
    -0.69
    helping
    -0.69
     Helps
    -0.67
     helped
    -0.65
    Helps
    -0.65
     facilitating
    -0.63
    POSITIVE LOGITS
    XmlAccessType
    0.76
    <bos>
    0.66
     verwijzen
    0.60
    Література
    0.58
    adaptiveStyles
    0.57
     CanadaChoose
    0.56
     limit
    0.52
    COUVER
    0.52
    IsContent
    0.52
     mean
    0.52
    Activations Density 3.224%

    No Known Activations