© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4233
    Prev
    Next
    INDEX
    Explanations

    mentions of things being supported with grants or trusts

    oai_token-act-pair · gemini-2.0-flash

    foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     half
    -0.86
     halves
    -0.85
    半分
    -0.76
    half
    -0.75
     halve
    -0.73
     نصف
    -0.73
     Half
    -0.72
     ModelExpression
    -0.71
     halved
    -0.70
    Half
    -0.68
    POSITIVE LOGITS
     foundations
    0.57
     foundation
    0.56
     يتيمه
    0.56
    }();
    0.54
     betweenstory
    0.53
     fondation
    0.53
    RTEX
    0.53
     Foundation
    0.51
    AlterField
    0.50
    ThroughAttribute
    0.49
    Activations Density 0.289%

    No Known Activations