© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14989
    Prev
    Next
    INDEX
    Explanations

    verbs related to personal experiences

    oai_token-act-pair · gemini-2.0-flash

    sequences or turns

    np_max-act · gemini-2.0-flash

    next

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.58
     (
    -0.57
     and
    -0.56
    <eos>
    -0.54
     for
    -0.49
    ,
    -0.47
    ↵
    -0.47
     in
    -0.42
     as
    -0.41
    1
    -0.40
    POSITIVE LOGITS
    +#+#
    1.23
     متعلقه
    1.16
    AndEndTag
    1.15
    IntoConstraints
    1.15
    endphp
    1.04
     ProtoMessage
    0.99
    LookAnd
    0.98
    IVEREF
    0.97
    rungsseite
    0.96
    TagHelper
    0.95
    Activations Density 1.599%

    No Known Activations