INDEX

Explanations

code snippets or URLs containing the letters 'e', 'm', 'p', 'r', 'u', and 's'

oai_token-act-pair · gemini-2.0-flash

code, errors

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Lieferumfang

-0.74

 Reine

-0.69

 벡터

-0.67

Удачи

-0.66

 Einer

-0.64

StructEnd

-0.64

Và

-0.63

 vectorielles

-0.63

 ModelExpression

-0.63

 Legge

-0.60

POSITIVE LOGITS

-------------</

0.65

 nahilalakip

0.63

lrrrr

0.63

 Cont

0.61

addPreferredGap

0.60

paramref

0.58

setVerticalGroup

0.58

Aff

0.57

sto

0.56

ึ้น

0.56

Activations Density 0.560%

code snippets or URLs containing the letters 'e', 'm', 'p', 'r', 'u', and 's'

code, errors

No Comments

No Known Activations