INDEX

Explanations

scientific publications

oai_token-act-pair · gemini-2.0-flash

punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

PerformLayout

-0.86

ंदीखरीदारी

-0.85

 nahilalakip

-0.80

GTCX

-0.69

ftagPool

-0.68

endpush

-0.67

principalTable

-0.67

AutoresizingMask

-0.66

WriteBarrier

-0.66

 kaynağından

-0.66

POSITIVE LOGITS

0.59

0.56

ed

0.55

losigkeit

0.54

<bos>

0.53

 Biochem

0.52

Bio

0.50

 Appl

0.50

 Moff

0.48

ocumented

0.48

Activations Density 12.770%

scientific publications

punctuation

No Comments

No Known Activations