© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6568
    Prev
    Next
    INDEX
    Explanations

    words related to conflict

    oai_token-act-pair · gemini-2.0-flash

    Code and academic references

    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
     gonna
    -1.79
     wanna
    -1.72
     GONNA
    -1.64
    gonna
    -1.45
     Gonna
    -1.42
     gotta
    -1.32
     kinda
    -1.26
     outta
    -1.23
    Gonna
    -1.15
     goin
    -1.13
    POSITIVE LOGITS
    örgy
    0.52
    liefert
    0.47
    BASEPATH
    0.46
     barbati
    0.46
     препратки
    0.46
    <tfoot>
    0.45
     متعلقه
    0.44
     esterni
    0.42
    enumi
    0.41
     sánchez
    0.40
    Activations Density 3.443%

    No Known Activations