INDEX

Explanations

a mix of domain-specific terms across varying topics, including genetics, coding, and chemistry

oai_token-act-pair · gemini-2.0-flash

biological research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Fordítás

-0.66

 ſtand

-0.63

 ſever

-0.63

 preſent

-0.63

 fhort

-0.62

 fubject

-0.61

 fhew

-0.60

 Shakspeare

-0.60

addCriterion

-0.59

 ſte

-0.59

POSITIVE LOGITS

HostException

0.61

 <>",

0.60

(!__

0.53

!*\

0.51

 mouseY

0.50

ГЛА

0.50

gatsby

0.49

SqlClient

0.48

CELLANEOUS

0.47

<eos>

0.47

Activations Density 1.976%

a mix of domain-specific terms across varying topics, including genetics, coding, and chemistry

biological research

No Comments

No Known Activations