INDEX

Explanations

opinionated or "deep" reviews or critiques, in the context of some art or media.

oai_token-act-pair · gemini-2.0-flash

writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 للاسماء

-0.72

yntaxException

-0.71

Efq

-0.70

 initComponents

-0.69

 Cæsar

-0.66

 '\\;'

-0.65

Personendaten

-0.65

WebVitals

-0.65

 متعلقه

-0.63

 OFDb

-0.62

POSITIVE LOGITS

<bos>

0.61

 base

0.56

hrens

0.50

 bases

0.48

aaS

0.46

use

0.45

@",

0.45

comed

0.45

go

0.45

 table

0.44

Activations Density 17.577%

opinionated or "deep" reviews or critiques, in the context of some art or media.

writing

No Comments

No Known Activations