INDEX

Explanations

scientific and technical writing and language.

oai_token-act-pair · gemini-2.0-flash

organic chemistry

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 InputDecoration

-0.67

 }}"></

-0.66

tvguidetime

-0.66

()));

-0.66

AddField

-0.65

 autorytatywna

-0.64

}')

-0.64

AutoScaleMode

-0.64

 combineReducers

-0.63

migrationBuilder

-0.62

POSITIVE LOGITS

GHIJKLM

0.66

NameInMap

0.56

 navideña

0.52

Efq

0.49

 whoſe

0.48

 natale

0.47

zulegen

0.47

hoben

0.47

InjectAttribute

0.47

testcase

0.46

Activations Density 2.433%

scientific and technical writing and language.

organic chemistry

No Comments

No Known Activations