INDEX

Explanations

phrases that connect humans and the environment

oai_token-act-pair · gemini-2.0-flash

environment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

onicus

-0.49

ilever

-0.47

િક

-0.46

บาง

-0.45

 balik

-0.45

ivamente

-0.44

manera

-0.44

 bevor

-0.44

存于互联网档案馆

-0.43

EXPERIMENT

-0.43

POSITIVE LOGITS

 AssemblyCulture

0.89

WithIOException

0.82

 doInBackground

0.73

 onPostExecute

0.73

IntoConstraints

0.69

 ProtoMessage

0.67

 InputDecoration

0.67

DoubleQuotes

0.65

MLLoader

0.65

principalColumn

0.61

Activations Density 1.119%

phrases that connect humans and the environment

environment

No Comments

No Known Activations