INDEX

Explanations

words related to places and people's names

oai_token-act-pair · gemini-2.0-flash

Places

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

 AspNetCore

-0.56

 насељу

-0.55

 joaat

-0.54

 onOptions

-0.53

Espèce

-0.52

 poveznice

-0.52

sunter

-0.52

iastes

-0.50

DrawerToggle

-0.50

Rgds

-0.50

POSITIVE LOGITS

ništvo

0.46

пр

0.46

orElseThrow

0.46

وصلات

0.46

 beginnetje

0.45

#+#

0.44

mazioni

0.44

]();

0.42

 históricos

0.42

XDECREF

0.42

Activations Density 8.721%

words related to places and people's names

Places

No Comments

No Known Activations