© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8558
    Prev
    Next
    INDEX
    Explanations

    first-person perspective of someone giving opinions about things, including the word 'things'

    oai_token-act-pair · gemini-2.0-flash

    non-English or programming language tokens

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

    things

    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
     lenker
    -0.56
    urop
    -0.52
    UVWXYZ
    -0.50
    WebVitals
    -0.49
    Insn
    -0.49
    例句
    -0.49
     Crosse
    -0.49
    URDAY
    -0.47
    ventus
    -0.47
    matorium
    -0.47
    POSITIVE LOGITS
    AutoField
    0.73
    AndEndTag
    0.66
    ⓧ
    0.64
    DebuggerNonUser
    0.62
     sauvages
    0.61
    سطس
    0.60
    ArgsConstructor
    0.59
     lær
    0.58
     vux
    0.55
     lär
    0.55
    Activations Density 7.715%

    No Known Activations