INDEX

Explanations

negative sentiment about conditions or results

oai_token-act-pair · gemini-2.0-flash

vanished

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

WriteLiteral

-0.51

 <<<<<<<<<<<<<<

-0.49

onAttach

-0.46

enial

-0.46

 unharmed

-0.45

lux

-0.44

 undamaged

-0.43

Pyx

-0.43

 breezes

-0.43

enciales

-0.43

POSITIVE LOGITS

 typelib

0.79

 kasarigan

0.76

PerformLayout

0.67

 Baillargeon

0.60

 محفوظة

0.60

 ComVisible

0.60

 visse

0.59

windowFixed

0.56

"]();

0.56

 للاسماء

0.56

Activations Density 3.728%

negative sentiment about conditions or results

vanished

No Comments

No Known Activations