INDEX

Explanations

terminology related to government, security and intelligence agencies, especially in the context of international relations and espionage.

oai_token-act-pair · gemini-2.0-flash

intelligence agencies

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

lapsingToolbar

-0.79

 nahilalakip

-0.77

GEBURTSDATUM

-0.70

rungsseite

-0.70

InvalidProtocol

-0.69

 ſeveral

-0.68

 Majefty

-0.68

 purpoſe

-0.68

Efq

-0.67

ContentAlignment

-0.66

POSITIVE LOGITS

 salient

0.46

MLLoader

0.41

raw

0.41

TabIndex

0.41

IRUS

0.40

 prom

0.40

 promising

0.40

â

0.39

form

0.39

Activations Density 34.426%

terminology related to government, security and intelligence agencies, especially in the context of international relations and espionage.

intelligence agencies

No Comments

No Known Activations