© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8646
    Prev
    Next
    INDEX
    Explanations

    code or program instructions

    oai_token-act-pair · gemini-2.0-flash

    code and paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
       
    -0.79
    }_{\
    -0.61
     }_{\
    -0.61
     AssemblyCulture
    -0.59
    #+#
    -0.54
     ***!
    -0.54
    ंदीखरीदारी
    -0.52
     nakalista
    -0.50
    ]_{
    -0.49
    _{\
    -0.49
    POSITIVE LOGITS
    exitRule
    0.59
    éndole
    0.57
     viață
    0.56
     متعلقه
    0.56
         
    0.54
     betweenstory
    0.54
     Normdatei
    0.51
    })^
    0.51
     őket
    0.51
    MIND
    0.51
    Activations Density 2.732%

    No Known Activations