© 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. 3052
    Prev
    Next
    INDEX
    Explanations

    Croatian/Slovenian text related to Facebook account verification via SMS

    oai_token-act-pair · gemini-2.0-flash

    Facebook account verification

    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
     
    -0.31
     (
    -0.30
     O
    -0.27
    /
    -0.26
     I
    -0.25
     and
    -0.24
     /
    -0.24
    <eos>
    -0.24
    ↵
    -0.24
     -
    -0.23
    POSITIVE LOGITS
     itſelf
    1.60
     myſelf
    1.59
     purpoſe
    1.58
     pleaſure
    1.56
     houſe
    1.48
     ſtate
    1.45
     themſelves
    1.45
     raiſ
    1.42
     Jefus
    1.40
     ſeveral
    1.39
    Activations Density 2.874%

    No Known Activations