INDEX

Explanations

code and configuration files

oai_token-act-pair · gemini-2.0-flash

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BioLib

-0.67

 wording

-0.67

 worded

-0.66

 pinulongan

-0.62

المناصب

-0.62

 PLWABN

-0.62

 narrowing

-0.60

FieldBuilder

-0.60

 narrows

-0.59

 broadest

-0.59

POSITIVE LOGITS

sizeCache

0.49

Memento

0.47

politan

0.46

 chapter

0.44

IBar

0.44

enswert

0.44

 виправивши

0.43

 STATUS

0.43

getSeconds

0.41

Demo

0.41

Activations Density 3.926%

code and configuration files

Code snippets

No Comments

No Known Activations