© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11447
    Prev
    Next
    INDEX
    Explanations

    strings that end in "nen", "isto", "via", and "pel", but also selects shorter strings that look like parts of proper names.

    oai_token-act-pair · gemini-2.0-flash

    names or entities related to locations

    np_token-act-pair-logits · gpt-4o-mini

    Finnish topics and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     CreateTagHelper
    -0.79
    setVerticalGroup
    -0.74
    protoc
    -0.65
    StructEnd
    -0.65
     ddelweddau
    -0.63
    पया
    -0.62
    astify
    -0.61
     AssemblyCulture
    -0.59
    NgModule
    -0.59
     فريبيس
    -0.57
    POSITIVE LOGITS
     Thương
    0.46
    níků
    0.44
     Signalez
    0.42
     courir
    0.41
    atalyst
    0.41
     Kalt
    0.41
     bianche
    0.41
    時半
    0.41
    CopyWith
    0.40
    +#+
    0.40
    Activations Density 0.176%

    No Known Activations