INDEX

Explanations

business names or fields of study

oai_token-act-pair · gemini-2.0-flash

business or organization names

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WriteTagHelper

-0.47

 bewegt

-0.45

 поворо

-0.44

 пове

-0.44

glieder

-0.44

 elder

-0.44

 verba

-0.43

</tfoot>

-0.43

DECLARE

-0.43

 welding

-0.42

POSITIVE LOGITS

fjspx

0.75

 gynhyrchwyd

0.69

MethodManager

0.69

 linkovi

0.67

 BIBSYS

0.66

URLException

0.65

NameInMap

0.64

LabelTagHelper

0.63

OGND

0.62

сылкі

0.62

Activations Density 1.441%

business names or fields of study

business or organization names

No Comments

No Known Activations