© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10026
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and phrases about people

    oai_token-act-pair · gemini-2.0-flash

    positive affirmations or qualities

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

    qualities of people

    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
    يكب
    -0.54
     pulumi
    -0.50
     transfieras
    -0.47
    venia
    -0.46
     poderão
    -0.46
     iprot
    -0.46
    toThrow
    -0.46
     discorso
    -0.45
    typeorm
    -0.45
    кипедия
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.73
    NgModule
    0.68
    rostis
    0.56
    संद
    0.54
     Signalez
    0.53
    __((
    0.53
    apnews
    0.52
    PositiveButton
    0.52
    atically
    0.51
    oples
    0.50
    Activations Density 0.942%

    No Known Activations