INDEX

Explanations

code snippets or discussions of code

oai_token-act-pair · gemini-2.0-flash

HTML and code elements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Element

-2.59

 Elements

-2.56

 element

-2.56

 elements

-2.45

element

-2.39

Elements

-2.33

elements

-2.31

 ELEMENTS

-2.31

Element

-2.28

元素

-2.05

POSITIVE LOGITS

Irlande

0.50

 pronti

0.46

 >=",

0.45

verwijspagina

0.45

 piele

0.45

 khawatir

0.44

likte

0.44

salvar

0.43

SaveChangesAsync

0.42

ungkapkan

0.42

Activations Density 1.539%

code snippets or discussions of code

HTML and code elements

No Comments

No Known Activations