INDEX

Explanations

historical or biographical information about people and places, especially locations and dates

oai_token-act-pair · gemini-2.0-flash

historical contexts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

elemField

-0.77

 Monfieur

-0.56

BufferException

-0.56

gameserver

-0.54

IVEREF

-0.53

rogels

-0.52

 Theſe

-0.52

DHL

-0.51

 dAtA

-0.50

 Boeing

-0.50

POSITIVE LOGITS

 تضيفلها

0.62

ScopeManager

0.59

gway

0.49

 autorytatywna

0.48

Mutagenicity

0.47

 eingestellt

0.47

 ljudi

0.46

 patrimoine

0.45

Erreferentziak

0.45

+:+

0.45

Activations Density 17.380%

historical or biographical information about people and places, especially locations and dates

historical contexts

No Comments

No Known Activations