© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    instances of someone admitting something

    oai_token-act-pair · gemini-2.0-flash

    admissions and confessions

    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
     admission
    -2.45
     admitting
    -2.39
     admit
    -2.28
     Admission
    -2.14
     admitted
    -2.14
     admissions
    -2.09
     Admit
    -2.00
    Admission
    -1.96
     admits
    -1.91
    admission
    -1.88
    POSITIVE LOGITS
    ad
    0.75
     AD
    0.69
    AD
    0.65
     Ad
    0.56
    Ad
    0.56
    ád
    0.55
     ad
    0.53
    createNewFile
    0.52
    BoxShadow
    0.50
    tigkeit
    0.47
    Activations Density 3.785%

    No Known Activations