INDEX

Explanations

code snippets, figures and study results

oai_token-act-pair · gemini-2.0-flash

numbers and code snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

protoimpl

-0.91

 autorytatywna

-0.85

tagHelperRunner

-0.85

 GenerationType

-0.81

outState

-0.77

LookAnd

-0.73

")));

-0.71

Bronnen

-0.71

 CreateTagHelper

-0.68

 Reſ

-0.66

POSITIVE LOGITS

rieux

0.47

pflicht

0.46

...

0.45

stateMutability

0.44

ộn

0.44

...

0.44

REDIRECT

0.43

Normalize

0.43

stylesheet

0.42

poxy

0.41

Activations Density 2.641%

code snippets, figures and study results

numbers and code snippets

No Comments

No Known Activations