INDEX

Explanations

words or symbols in technical documents related to math, machinery, office work, or crime

oai_token-act-pair · 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

IVEREF

-0.87

 Infórmanos

-0.82

 PagesJaunes

-0.74

RTDA

-0.73

InputTagHelper

-0.73

ьаж

-0.69

CloseOperation

-0.67

 дописавши

-0.66

 חיצוניים

-0.62

sizeCache

-0.62

POSITIVE LOGITS

NOPQRST

0.54

 halbe

0.49

 unarmed

0.49

 antaranya

0.49

 flèche

0.49

ządu

0.48

 sonore

0.46

 blé

0.46

ויים

0.46

 Одно

0.45

Activations Density 16.595%

words or symbols in technical documents related to math, machinery, office work, or crime

No Comments

No Known Activations