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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14076
    Prev
    Next
    INDEX
    Explanations

    context and conversational cues

    oai_token-act-pair · gemini-2.0-flash

    Continuations

    np_max-act-logits · gemini-2.0-flash

    prepositions

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    sstream
    -0.39
    marginHorizontal
    -0.34
    alignSelf
    -0.32
    onCancel
    -0.29
    beforeSend
    -0.28
    marginVertical
    -0.27
    isString
    -0.26
    wantErr
    -0.25
    removeAttr
    -0.25
    startAnimation
    -0.25
    POSITIVE LOGITS
    space
    0.88
    shots
    0.85
    shot
    0.85
    head
    0.84
    book
    0.84
    group
    0.84
    power
    0.82
    runners
    0.82
    play
    0.82
    ground
    0.82
    Activations Density 78.342%

    No Known Activations