© 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. 5836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an overwhelmingly positive review with a focus on accolades

    oai_token-act-pair · gemini-2.0-flash

    Justice/Deserving

    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
     deserve
    -1.39
     deserved
    -1.20
     deserves
    -1.20
     deserving
    -1.14
    deserved
    -1.05
     equivalent
    -0.96
     Equivalent
    -0.93
     merit
    -0.90
     mérit
    -0.89
    equivalent
    -0.88
    POSITIVE LOGITS
    èdia
    0.60
     transfieras
    0.54
    Fully
    0.52
    UnknownFieldSet
    0.49
    Vegeu
    0.49
     Exactos
    0.49
     fully
    0.48
     Fully
    0.48
    GetError
    0.46
    Begriffsklä
    0.46
    Activations Density 8.180%

    No Known Activations