INDEX

Explanations

a mix of tokens related to software installation and legal documents

oai_token-act-pair · gemini-2.0-flash

code, legal documents

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

 bezeichneter

-0.71

 المعيارى

-0.60

 ویکی‌آمباردا

-0.60

RenderAtEndOf

-0.60

évaluateur

-0.58

ValueStyle

-0.52

তথ্যসূত্র

-0.52

absl

-0.52

 natomiast

-0.50

Cllr

-0.48

POSITIVE LOGITS

GetMapping

0.57

InjectAttribute

0.55

NOPQRST

0.54

cating

0.54

 Swimming

0.54

 Sensing

0.54

complexType

0.52

CreateMap

0.52

beth

0.52

زم

0.52

Activations Density 5.973%

a mix of tokens related to software installation and legal documents

code, legal documents

No Comments

No Known Activations