INDEX

Explanations

a mix of numbers, letters, and punctuation possibly related to models, versions, or IDs

oai_token-act-pair · gemini-2.0-flash

F

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

 CURIAM

-0.58

 سكانية

-0.56

__.__

-0.52

"},

-0.52

nodoc

-0.52

uebe

-0.52

")));

-0.52

zeptember

-0.51

 another

-0.51

viewtopic

-0.50

POSITIVE LOGITS

Personensuche

0.58

SourceChecksum

0.54

 specchio

0.54

BeginContext

0.52

ugal

0.52

 onResponse

0.52

 विश्वसनीयता

0.52

Források

0.50

 ordini

0.49

netbeans

0.48

Activations Density 1.920%

a mix of numbers, letters, and punctuation possibly related to models, versions, or IDs

F

No Comments

No Known Activations