© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8526
    Prev
    Next
    INDEX
    Explanations

    words related to studies, healthcare and the keys to success

    oai_token-act-pair · gemini-2.0-flash

    key

    np_max-act-logits · gemini-2.0-flash
    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
     key
    -2.56
    key
    -2.16
     Key
    -2.14
    Key
    -2.09
    KEY
    -1.91
     KEY
    -1.90
     keys
    -1.41
     chiave
    -1.38
    キー
    -1.30
     clés
    -1.28
    POSITIVE LOGITS
    InitStruct
    0.57
    DI
    0.49
    dera
    0.45
    estanden
    0.45
    bes
    0.45
    di
    0.44
    =$?
    0.43
    су
    0.42
    couver
    0.42
     DI
    0.41
    Activations Density 7.489%

    No Known Activations