© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7647
    Prev
    Next
    INDEX
    Explanations

    the word "permission" and sometimes the word "the"

    oai_token-act-pair · gemini-2.0-flash

    permission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     "
    -0.75
     
    -0.74
     N
    -0.69
     (
    -0.67
     non
    -0.65
     a
    -0.65
     “
    -0.63
     I
    -0.63
     He
    -0.63
     S
    -0.62
    POSITIVE LOGITS
     ainfi
    1.16
    Portale
    0.97
     feroit
    0.96
    WebVitals
    0.90
    HomeAsUpEnabled
    0.90
     auroit
    0.89
     rheumatism
    0.89
     subgoals
    0.89
     <<<<<<<<<<<<<<
    0.89
     Opis
    0.86
    Activations Density 1.312%

    No Known Activations