© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10426
    Prev
    Next
    INDEX
    Explanations

    the words "there", "are", "you" and "it"

    oai_token-act-pair · gemini-2.0-flash

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TagMode
    -0.63
    schirm
    -0.57
     itſelf
    -0.56
    mentaux
    -0.55
     ocasião
    -0.51
     themſelves
    -0.50
    DataMember
    -0.50
    ajte
    -0.50
    infan
    -0.49
     frattempo
    -0.49
    POSITIVE LOGITS
    DataAnnotations
    0.58
    fromCharCode
    0.56
    endphp
    0.53
     snippetHide
    0.52
    awtextra
    0.52
    migrationBuilder
    0.51
     tenuto
    0.51
     arises
    0.50
    DOCTYPE
    0.50
    interopRequire
    0.50
    Activations Density 0.234%

    No Known Activations