© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7572
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "heart" and to a lesser extent, other words associated with strong emotion or the body, like "gut" or "breath".

    oai_token-act-pair · gemini-2.0-flash

    heart

    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
     himo
    -0.53
    脚注の使い方
    -0.52
     Josephus
    -0.49
     ngang
    -0.46
    цима
    -0.44
     conflits
    -0.44
    ize
    -0.43
     aktivitet
    -0.43
    Xa
    -0.42
     pouvoirs
    -0.42
    POSITIVE LOGITS
    цездатний
    0.69
    </tfoot>
    0.66
    kwds
    0.60
     Roskov
    0.59
    DebuggerNonUser
    0.58
    Iné
    0.58
     HasFactory
    0.56
     laure
    0.55
    ChildScrollView
    0.54
     fistula
    0.54
    Activations Density 5.645%

    No Known Activations