© 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. 596
    Prev
    Next
    INDEX
    Explanations

    a blend of English and Indonesian languages in an informal style

    oai_token-act-pair · gemini-2.0-flash

    foreign languages/code

    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
    הערות
    -0.45
    }=(
    -0.44
     giáp
    -0.40
     []:
    -0.40
    ke
    -0.36
    vane
    -0.35
     Wel
    -0.35
    
    -0.35
     Dal
    -0.33
     آم
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    0.96
     ſche
    0.88
     itſelf
    0.85
     pleaſure
    0.85
     purpoſe
    0.85
    ſelf
    0.85
     himſelf
    0.84
    +:+
    0.82
     Majefty
    0.82
     myſelf
    0.81
    Activations Density 0.175%

    No Known Activations