INDEX

Explanations

code snippets and programming language syntax.

oai_token-act-pair · gemini-2.0-flash

code

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

ashes

-0.54

 חיצוניים

-0.51

 була

-0.47

 henvisninger

-0.46

 multic

-0.45

 houſe

-0.45

 itſelf

-0.44

 Houſe

-0.44

fish

-0.44

 Catalana

-0.44

POSITIVE LOGITS

Cyfeiriadau

0.77

AccessorTable

0.74

 HttpNotFound

0.70

ंदीखरीदारी

0.69

 ModelExpression

0.67

AutoField

0.67

rungsseite

0.67

 propOrder

0.66

sizeCache

0.65

OGND

0.64

Activations Density 8.873%

code snippets and programming language syntax.

code

No Comments

No Known Activations